Release latent-first H3 Continuum V3
This commit is contained in:
@@ -1,585 +1,230 @@
|
||||
# ComfyUI-H3-Continuum 2.1.7
|
||||
# ComfyUI-H3-Continuum 3.0.0
|
||||
|
||||
Native long-form MiniMax H3 video and audio continuation for ComfyUI.
|
||||
Long-form native MiniMax H3 video and audio continuation for ComfyUI.
|
||||
|
||||
**H3 Continuum Sampler** generates 1 to 16 H3 chunks as one sequence. It carries the previous raw video and audio latent into the next chunk, keeps accepted chunk latents on CPU, and defers VAE decoding until sampling is complete.
|
||||
V3 is a latent-first workflow. It samples several manageable H3 chunks, carries raw video and audio context into each continuation chunk, and sends the complete raw chunks to ComfyUI Core VAE nodes for decoding. **H3 Continuum Assemble V3** then trims decoded context, aligns audio, and produces the final video frames and audio.
|
||||
|
||||
<!-- h3-standard-workflow -->
|
||||
## Standard workflow
|
||||
## V3 highlights
|
||||
|
||||
[Download the standard **H3 Continuum V2** template bundle](examples/H3_Continuum_V2.zip) (recommended).
|
||||
- Generate 1 to 16 native H3 chunks as one continuous sequence.
|
||||
- Preserve raw paired video/audio latent context without decode and re-encode between chunks.
|
||||
- Keep accepted full chunk latents on CPU instead of accumulating them in active VRAM.
|
||||
- Use ComfyUI Core **VAE Decode** or **VAE Decode (Tiled)** for video.
|
||||
- Use ComfyUI Core **VAE Decode Audio** for audio.
|
||||
- Trim decoded overlap and assemble the final result with cumulative audio sample alignment.
|
||||
- Optionally accelerate sampling with external SageAttention and Spectrum nodes.
|
||||
- Automatically request Spectrum Actual Prefix 2 for continuation chunks.
|
||||
- Preserve V1/V2 node identifiers and State/Session schema compatibility.
|
||||
|
||||
[Download the workflow JSON only](examples/H3_Continuum_V2.json).
|
||||
|
||||
The ZIP contains the workflow, its reference image, and a short setup guide. Extract it, copy `H3_Continuum_V2_reference.webp` into `ComfyUI/input/`, then drag `H3_Continuum_V2.json` onto the ComfyUI canvas.
|
||||
|
||||
It is a practical 3 x 5-second starting point for compatible MiniMax H3 ComfyUI systems. The bundled profile was validated on an RTX 5060 Ti 16GB system with 64GB of system RAM, but the workflow is not limited to that GPU. Adjust `chunks`, `chunk_seconds`, resolution, seed, prompts, and optional accelerators to suit the available hardware. The graph uses the stable facade nodes and keeps session, reroll, and report wiring optional.
|
||||
|
||||
Related projects:
|
||||
|
||||
- [ComfyUI Spectrum MiniMax H3](https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3) is the optional sampling accelerator used by the bundled graph.
|
||||
|
||||
### Models referenced by the workflow
|
||||
|
||||
All model URLs stored in the JSON point to the `Comfy-Org/MiniMax-H3` distribution used for ComfyUI workflows. No third-party checkpoint host is referenced:
|
||||
|
||||
- `diffusion_models/minimax/minimax_h3_fl2va_pruned_int8_convrot.safetensors`
|
||||
- `text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`
|
||||
- `vae/minimax_h3_video_vae_fp16.safetensors`
|
||||
- `vae/minimax_h3_audio_vae_fp32.safetensors`
|
||||
|
||||
No model weights are bundled in this repository. The workflow also contains optional/custom helper nodes from Spectrum, KJNodes (Sage Attention), rgthree, and ComfyUI-Easy-Use. Install those packages or replace/bypass their helper nodes.
|
||||
|
||||
## Why H3 Continuum exists
|
||||
|
||||
**H3 Continuum Sampler is an integrated sampler that includes H3 sampling, deferred Video/Audio VAE decoding, Context trimming, and automatic multi-chunk assembly.** The VAE model weights are not bundled or loaded internally; connect externally loaded `video_vae` and `audio_vae` inputs.
|
||||
|
||||
Continuum was created to make SVI-style long-form continuation practical with native MiniMax H3: generate several manageable chunks, carry motion and audio context forward, and assemble one result without manually rebuilding the graph for every clip.
|
||||
|
||||
The main benefit is not only continuity. A native monolithic 15-second H3 generation can put substantial pressure on VRAM. Continuum samples shorter chunks separately, carries only the required raw AV latent context, stores completed chunk data outside the active sampling path, and defers decoding until sampling is complete. This can make a 3 x 5-second sequence less likely to run out of VRAM on a 16GB GPU, although resolution, model precision, accelerators, offload settings, and available system RAM still determine the actual limit.
|
||||
|
||||
The standard workflow uses the INT8 ConvRot H3 checkpoint, SageAttention CUDA++, and optional Spectrum acceleration as the validated reference profile. On different GPUs or software stacks, start with SageAttention `Auto` or bypass optional accelerators and confirm compatibility locally. Spectrum is not required for continuity and should be disabled for native-trajectory quality comparisons.
|
||||
|
||||
Continuum was developed independently around its integrated multi-chunk workflow, AV timeline validation, and compatibility requirements. Other H3 continuation approaches are discussed only where their workflow and implementation differences are relevant.
|
||||
|
||||
## Recommended quality-first profile
|
||||
|
||||
Continuum targets a useful reduction in long-form generation time while retaining comparatively high quality. It does not select every available accelerator for maximum speed.
|
||||
|
||||
| Component | Bundled RTX 5060 Ti profile | General recommendation |
|
||||
| --- | --- | --- |
|
||||
| MiniMax H3 model | `minimax_h3_fl2va_pruned_int8_convrot.safetensors` | Use a compatible official H3 model; the INT8 ConvRot build is the tested 16GB profile. |
|
||||
| SageAttention | `sageattn_qk_int8_pv_fp8_cuda++`, compile off | Use `Auto` when the installed SageAttention build and GPU-specific backend are unknown. |
|
||||
| Spectrum | Enabled with the settings below | Optional; disable it for a native-trajectory quality reference. |
|
||||
| Sol-Attn | Disabled | Currently not recommended in the standard continuity profile. Local A/B runs showed more visible boundary artifacts in some outputs; this is not a universal incompatibility claim. |
|
||||
| Turbo LoRA | Disabled | Not tested with this Continuum profile. No quality or compatibility claim is made yet. |
|
||||
| Seam Correction | `Auto` | Safe general starting point. In the current local A/B sample, `Off` produced the least noticeable visual boundary. Compare `Auto` and `Off` first. |
|
||||
|
||||
Recommended Spectrum values used by this profile:
|
||||
## Standard V3 connection
|
||||
|
||||
```text
|
||||
blend_weight = 0.50
|
||||
warmup_steps = 1
|
||||
offline_smoothing_replay = true
|
||||
bootstrap_first_forecast = true
|
||||
audio_blend_weight = 0.00
|
||||
H3 MODEL
|
||||
-> optional SageAttention
|
||||
-> optional Spectrum
|
||||
-> H3 Continuum Sampler V3.model
|
||||
|
||||
CLIP / text encoder ----------------------> Sampler V3.clip
|
||||
MiniMax H3 Video VAE --------------------> Sampler V3.video_vae
|
||||
Sampler ---------------------------------> Sampler V3.sampler
|
||||
Sigmas ----------------------------------> Sampler V3.sigmas
|
||||
Text (Multiline) ------------------------> Sampler V3.Sequence Prompt
|
||||
Scaled source image ---------------------> Sampler V3.first_frame
|
||||
|
||||
Sampler V3.video_latents ---------------> Core VAE Decode.samples
|
||||
MiniMax H3 Video VAE --------------------> Core VAE Decode.vae
|
||||
|
||||
Sampler V3.audio_latents ---------------> Core VAE Decode Audio.samples
|
||||
MiniMax H3 Audio VAE --------------------> Core VAE Decode Audio.vae
|
||||
|
||||
Core VAE Decode.IMAGE -------------------> Assemble V3.images
|
||||
Core VAE Decode Audio.AUDIO -------------> Assemble V3.audio
|
||||
Sampler V3.assembly_plan ----------------> Assemble V3.assembly_plan
|
||||
|
||||
Assemble V3.images ----------------------> Create Video.images
|
||||
Assemble V3.audio -----------------------> Create Video.audio
|
||||
```
|
||||
|
||||
Continuum automatically requests Actual Prefix 2 for continuation chunks. This is not an extra user-facing Spectrum setting and does not increase the configured solver-step count.
|
||||
The grid marker on `video_latents` and `audio_latents` means that each output is a chunk list. ComfyUI automatically maps the Core VAE Decode nodes across that list. You do not need to duplicate the decode nodes for every chunk.
|
||||
|
||||
### Seam Correction A/B note
|
||||
`video_vae` remains connected to the sampler because V3 uses it to encode first-frame and optional last-frame conditioning. V3 does not use it for output decoding.
|
||||
|
||||
The bundled workflow keeps `Auto` as a conservative general default. In the current 3 x 5-second local comparison, however, `Off` gave the most natural-looking join. `Auto` may apply a measured color adjustment or short blend that improves its numeric seam score but is not always preferred by visual inspection.
|
||||
## Main nodes
|
||||
|
||||
For a new model, prompt, resolution, or accelerator combination, render the same seed with `Auto` and `Off`. Prefer `Off` when Native Continuity already produces a clean boundary; use `Auto` when it visibly reduces a remaining luminance, color, or audio discontinuity.
|
||||
### H3 Continuum Sampler V3
|
||||
|
||||
## Quick start
|
||||
Runs H3 sampling and native continuation, then outputs:
|
||||
|
||||
1. Install the custom node and restart ComfyUI.
|
||||
2. Add **H3 Continuum Sampler**.
|
||||
3. Connect the normal H3 model, CLIP, VAEs, sampler, and sigmas.
|
||||
4. Connect one **Text (Multiline)** node to **Sequence Prompt**.
|
||||
5. For image-to-video, connect the source image to **first_frame**.
|
||||
6. Connect **images** and **audio** to your normal video output node.
|
||||
7. Start with two 5-second chunks and the settings shown below.
|
||||
|
||||
Most users only need **H3 Continuum Sampler**. The helper nodes are optional.
|
||||
|
||||
## Installation
|
||||
|
||||
### Git installation
|
||||
|
||||
From the ComfyUI custom_nodes directory:
|
||||
|
||||
~~~bash
|
||||
git clone https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum.git
|
||||
~~~
|
||||
|
||||
Restart ComfyUI, then search for **H3 Continuum Sampler**.
|
||||
|
||||
For Stability Matrix, the destination is normally similar to:
|
||||
|
||||
~~~text
|
||||
D:\StabilityMatrix\Data\Packages\<ComfyUI package>\custom_nodes\
|
||||
~~~
|
||||
|
||||
### ZIP or Windows installer
|
||||
|
||||
1. Extract the repository as **ComfyUI-H3-Continuum**.
|
||||
2. Place it in **ComfyUI/custom_nodes/**.
|
||||
3. Run **install_windows.bat** if you want the included Windows installer to copy and validate the package.
|
||||
4. Restart ComfyUI.
|
||||
|
||||
If an older **ComfyUI-H3-Continuum-Join** folder exists, remove or rename it before starting ComfyUI. Do not load both folders at the same time.
|
||||
|
||||
No additional pip packages are required beyond the normal ComfyUI MiniMax H3 environment.
|
||||
|
||||
## Standard connection
|
||||
|
||||
~~~text
|
||||
H3 MODEL loader
|
||||
|
|
||||
+-> optional SageAttention
|
||||
+-> optional Sol-Attn
|
||||
+-> optional LoRA
|
||||
+-> optional Spectrum
|
||||
|
|
||||
v
|
||||
H3 Continuum Sampler.model
|
||||
|
||||
CLIP loader -----------------------> clip
|
||||
MiniMax H3 Video VAE -------------> video_vae
|
||||
MiniMax H3 Audio VAE -------------> audio_vae
|
||||
Sampler --------------------------> sampler
|
||||
Sigmas ---------------------------> sigmas
|
||||
Text (Multiline) -----------------> Sequence Prompt
|
||||
Load Image -----------------------> first_frame
|
||||
|
||||
H3 Continuum Sampler.images ------> Create Video.images
|
||||
H3 Continuum Sampler.audio -------> Create Video.audio
|
||||
~~~
|
||||
|
||||
The accelerator chain is optional. A typical accelerated order is:
|
||||
|
||||
~~~text
|
||||
H3 MODEL -> SageAttention -> Sol-Attn -> LoRA -> Spectrum
|
||||
~~~
|
||||
|
||||
When troubleshooting, start with fewer accelerators and add them back one at a time.
|
||||
|
||||
### Main inputs
|
||||
|
||||
| Input | Connect |
|
||||
| Output | Purpose |
|
||||
| --- | --- |
|
||||
| **model** | The final MODEL from the normal H3 model or accelerator chain |
|
||||
| **clip** | MiniMax H3 text encoder / CLIP output |
|
||||
| **video_vae** | MiniMax H3 Video VAE |
|
||||
| **audio_vae** | MiniMax H3 Audio VAE |
|
||||
| **sampler** | The sampler used by the normal H3 workflow |
|
||||
| **sigmas** | The corresponding sigma schedule |
|
||||
| **Sequence Prompt** | One external Text (Multiline) STRING |
|
||||
| **first_frame** | Source image for image-to-video |
|
||||
| **prompt_overrides** | Optional H3 Continuum Clip Overrides pack |
|
||||
| **advanced** | Optional H3 Continuum Advanced pack |
|
||||
| `video_latents` | Full raw video latent chunks for Core VAE Decode |
|
||||
| `audio_latents` | Full raw audio latent chunks for Core VAE Decode Audio |
|
||||
| `assembly_plan` | Context trim and exact-duration contract for Assemble V3 |
|
||||
| `result` | Optional packed State, Session, and sampler report |
|
||||
|
||||
### Main outputs
|
||||
### H3 Continuum Assemble V3
|
||||
|
||||
| Output | Use |
|
||||
| --- | --- |
|
||||
| **images** | Connect directly to the image/video frames input of the output node |
|
||||
| **audio** | Connect directly to the audio input of the output node |
|
||||
| **result** | Optional packed State, Session, and report data |
|
||||
Receives all externally decoded chunks and:
|
||||
|
||||
<!-- h3-node-guide -->
|
||||
## Sampler and Advanced controls
|
||||
- validates chunk counts against the assembly plan;
|
||||
- trims the decoded continuation context;
|
||||
- aligns audio using cumulative frame boundaries;
|
||||
- optionally applies **Audio Seam Auto** without changing video frames;
|
||||
- adjusts the final output to the requested exact duration.
|
||||
|
||||
### Input image scaling
|
||||
### H3 Continuum Advanced V3
|
||||
|
||||

|
||||
|
||||
The bundled workflow uses **Scale Image to Total Pixels** before `first_frame`:
|
||||
|
||||
- `upscale_method: area` is appropriate for reducing a larger source image with stable averaging.
|
||||
- `megapixels: 0.50` preserves the source aspect ratio while targeting approximately 0.5 million pixels.
|
||||
- `resolution_steps: 32` rounds width and height to model-friendly multiples of 32.
|
||||
- The bundled portrait is reduced from 848 x 1264 to approximately 576 x 864; the exact rounded size is supplied to the Continuum sampler through the image-size nodes.
|
||||
- If a 16GB GPU runs out of VRAM, reduce this first to `0.30 MP`, which is approximately 448 x 672 for the same portrait.
|
||||
|
||||
This node changes generation resolution, not the Continuum context length. Increasing megapixels raises VRAM use and generation time for every chunk.
|
||||
|
||||
The screenshot shows the same control at 0.60 MP for illustration. The current bundled JSON uses 0.50 MP.
|
||||
|
||||

|
||||
|
||||
The main sampler is sufficient for a normal first run:
|
||||
|
||||
- `Sequence Prompt`: one fixed prompt, a `---`-separated list, or a timeline prompt.
|
||||
- `Prompt Format`: `Auto` is the recommended default.
|
||||
- `chunks`: number of generated clips.
|
||||
- `chunk_seconds`: requested duration of each clip.
|
||||
- `width` / `height`: inherited from the connected image-size path when linked.
|
||||
- `continuity`: `Balanced - 22 frames` is the general-purpose default.
|
||||
- `base_seed` and `control after generate`: define the chunk seed sequence.
|
||||
- `seam_correction`: `Auto` is the safe default; it keeps the legacy video seam when correction does not improve the measured boundary.
|
||||
- `prompt_overrides`: optional sparse per-clip replacement pack.
|
||||
- `advanced`: optional settings pack. Leave it disconnected to use normal defaults.
|
||||
|
||||

|
||||
|
||||
Use **H3 Continuum Advanced** only when the basic node is not enough:
|
||||
|
||||
- `last_frame`: optional final-frame anchor.
|
||||
- `session`: resumes or reuses a Continuum session.
|
||||
- `initial_state`: begins from a saved Continuum state.
|
||||
- `prompt_plan`: accepts an externally prepared prompt plan.
|
||||
- `audio_continuity`: keeps audio context across chunk boundaries.
|
||||
- `exact_total_duration`: trims or pads the assembled result to the requested duration.
|
||||
- `Report Detail`: `Basic` is the standard default. Use Detailed Report only for troubleshooting.
|
||||
- `reroll_from_chunk`: regenerates from a selected chunk; `0` disables reroll.
|
||||
- `reroll_nonce`: changes a reroll without replacing the main seed.
|
||||
- `strict_compatibility`: fails closed when the native H3 layout contract is incompatible.
|
||||
- `debug`: enables additional diagnostic logging.
|
||||
- `show_preview`: enables the sampling preview.
|
||||
|
||||
### Wiring reminder
|
||||
|
||||
For a standard graph, connect the patched MODEL path to `model`, the MiniMax H3 text encoder to `clip`, the video/audio VAEs to their matching inputs, the sampler and sigmas, a multiline text node to `Sequence Prompt`, and the scaled source image to `first_frame`. Connect `images` and `audio` to Create Video or Save Video.
|
||||
|
||||
`prompt_overrides`, `advanced`, and the Result helper are optional. Use **H3 Continuum Result** only when you need `last_state`, `session`, or the text report.
|
||||
|
||||
## Recommended first run
|
||||
|
||||
| Setting | Recommended value |
|
||||
| --- | --- |
|
||||
| **Prompt Format** | Auto |
|
||||
| **chunks** | 2 |
|
||||
| **chunk_seconds** | 5.0 |
|
||||
| **width / height** | Match the intended H3 generation resolution |
|
||||
| **continuity** | Balanced - 22 frames |
|
||||
| **base_seed** | Fixed while comparing settings |
|
||||
| **control after generate** | fixed for A/B testing |
|
||||
| **seam_correction** | Auto for normal use |
|
||||
|
||||
This produces approximately 10 seconds.
|
||||
|
||||
For a native-continuity comparison, use the same prompt and seed and compare:
|
||||
|
||||
~~~text
|
||||
Seam Correction = Off
|
||||
Seam Correction = Auto
|
||||
~~~
|
||||
|
||||
**Auto** is the normal recommendation. It keeps the native seam unless the guarded correction produces a safely measurable improvement.
|
||||
|
||||
### Seam Correction modes
|
||||
|
||||
- **Auto**: Native-first mode. Applies post-decode correction only when the guarded candidate improves the measured seam.
|
||||
- **Off**: No post-decode seam correction. Use this to inspect Native Continuity directly.
|
||||
- **Basic**: Runs the V2.1 seam-correction path directly.
|
||||
|
||||
### Continuity profiles
|
||||
|
||||
- **Auto - conservative**: Chooses a conservative context profile from the previous state.
|
||||
- **Fast - 5 frames**: Lowest overlap and lowest continuity cost.
|
||||
- **Balanced - 22 frames**: Recommended starting point.
|
||||
- **Strong - 39 frames**: More context, with higher cost and a greater risk of over-constraining motion.
|
||||
|
||||
## Sequence Prompt
|
||||
|
||||
Connect a single **Text (Multiline)** node to **Sequence Prompt**.
|
||||
|
||||
### Auto
|
||||
|
||||
Auto detects Fixed, List, or Timeline syntax. This is recommended for normal use.
|
||||
|
||||
### Fixed
|
||||
|
||||
One prompt is used for every chunk.
|
||||
|
||||
~~~text
|
||||
A single continuous cinematic performance. Preserve the same person,
|
||||
lighting, camera direction, motion, voice, and music across every chunk.
|
||||
~~~
|
||||
|
||||
### List
|
||||
|
||||
Separate one prompt per chunk with a line containing three hyphens.
|
||||
|
||||
~~~text
|
||||
The woman begins singing while the camera slowly pushes in.
|
||||
---
|
||||
She continues the same phrase without a cut, reset, or pose jump.
|
||||
---
|
||||
She resolves the final note naturally and releases a soft breath.
|
||||
~~~
|
||||
|
||||
If fewer List sections are supplied than the configured chunk count, the last section is reused.
|
||||
|
||||
### Timeline
|
||||
|
||||
Use time or chunk sections in one multiline prompt.
|
||||
|
||||
~~~text
|
||||
[0-5s]
|
||||
The woman begins singing. The piano phrase remains unresolved.
|
||||
|
||||
[5-10s]
|
||||
Continue from the exact preceding breath, pose, camera movement, and melody.
|
||||
|
||||
[10-15s]
|
||||
Complete the melody naturally during the final second.
|
||||
~~~
|
||||
|
||||
Chunk headers are also accepted:
|
||||
|
||||
~~~text
|
||||
[Chunk 1]
|
||||
Opening action.
|
||||
|
||||
[Chunk 2]
|
||||
Continuous middle action.
|
||||
|
||||
[Chunk 3]
|
||||
Natural ending.
|
||||
~~~
|
||||
|
||||
## How continuation works
|
||||
|
||||
For every continuation chunk, Continuum:
|
||||
|
||||
1. Reads the accepted previous raw H3 video and audio latent.
|
||||
2. Extracts a phase-valid video and audio context window.
|
||||
3. Adds that context as fixed reference rows.
|
||||
4. Keeps new target audio and video rows separate and writable.
|
||||
5. Clones the workflow MODEL once for the current chunk.
|
||||
6. Samples the next chunk without decoding and re-encoding the prior result.
|
||||
7. Stores the accepted full chunk latent on CPU.
|
||||
8. Decodes and assembles all accepted chunks after sampling finishes.
|
||||
|
||||
The workflow input MODEL is not modified. Each chunk clone has its own Spectrum runtime/history.
|
||||
|
||||
When valid continuation context exists, Continuum emits Spectrum Interop API v1 with an Actual Prefix request of 2. Older or unsupported Spectrum versions ignore the hint and continue normally.
|
||||
|
||||
## Optional helper nodes
|
||||
|
||||
These nodes are not needed for the basic workflow.
|
||||
Optional pack for Session/State input, reroll controls, diagnostics, audio continuity, strict compatibility, and sampling preview control. Leave it disconnected for normal defaults.
|
||||
|
||||
### H3 Continuum Clip Overrides
|
||||
|
||||
Use this only when selected clips need prompts different from the main Sequence Prompt.
|
||||
|
||||
Connect one **Text (Multiline)** to **Override Script** and use explicit sparse sections:
|
||||
|
||||
~~~text
|
||||
[Clip 2]
|
||||
Move to a closer shot while preserving the same motion and voice.
|
||||
|
||||
[Clip 5]
|
||||
Finish the song naturally and hold the final note.
|
||||
~~~
|
||||
|
||||
Only Clip 2 and Clip 5 are replaced. All unspecified clips continue using the main Sequence Prompt.
|
||||
|
||||
**[Chunk N]** is also accepted. Duplicate clip numbers and clip numbers outside the configured chunk count are rejected.
|
||||
|
||||
Connect the pack output to **H3 Continuum Sampler.prompt_overrides**.
|
||||
|
||||
### H3 Continuum Advanced
|
||||
|
||||
Use this node for resume data and infrequent controls. Connect its output to **H3 Continuum Sampler.advanced**.
|
||||
|
||||
Important controls include:
|
||||
|
||||
- **last_frame**: Optional final-frame anchor for the final chunk.
|
||||
- **session**: Continue or reroll from a prior V2 Session.
|
||||
- **initial_state**: Start from a compatible saved State. Do not connect both Session and Initial State.
|
||||
- **prompt_plan**: Advanced or compatibility prompt-plan input.
|
||||
- **audio_continuity**: Continue the prior raw audio latent.
|
||||
- **exact_total_duration**: Correct the assembled output to the requested total duration.
|
||||
- **diagnostics**: Basic, Detailed Report, or Off.
|
||||
- **reroll_from_chunk**: Keep accepted earlier chunks and regenerate from this one-based chunk number.
|
||||
- **reroll_nonce**: Derive a different reroll seed without changing the base seed.
|
||||
- **strict_compatibility**: Stop on unknown or unsafe H3 layout contracts.
|
||||
- **debug**: Enable internal diagnostic logging.
|
||||
- **show_preview**: Enable the normal sampling preview.
|
||||
Optional sparse per-clip prompt replacement. Unspecified clips continue using the main Sequence Prompt.
|
||||
|
||||
### H3 Continuum Result
|
||||
|
||||
Connect the Sampler **result** output when you need to expose:
|
||||
Optional helper that exposes `last_state`, `session`, and the sampler report from the packed `result` output.
|
||||
|
||||
- **last_state**
|
||||
- **session**
|
||||
- **report**
|
||||
## Recommended starting settings
|
||||
|
||||
For ordinary final video generation, this node is unnecessary.
|
||||
| Setting | Starting value |
|
||||
| --- | --- |
|
||||
| Prompt Format | `Auto` |
|
||||
| Chunks | `2` or `3` for the first run |
|
||||
| Chunk seconds | `5.0` |
|
||||
| Continuity | `Balanced - 22 frames` |
|
||||
| Audio Seam | `Off` |
|
||||
| Exact total duration | `true` |
|
||||
| Report Detail | `Basic` |
|
||||
| Resolution | Approximately `0.5 MP` for practical detail |
|
||||
|
||||
## Sessions and rerolling
|
||||
|
||||
A Session stores accepted CPU latents, prompts, seeds, dimensions, and continuation metadata.
|
||||
|
||||
Typical advanced use:
|
||||
|
||||
~~~text
|
||||
H3 Continuum Sampler.result
|
||||
-> H3 Continuum Result.session
|
||||
-> H3 Continuum Save Session
|
||||
~~~
|
||||
|
||||
Later:
|
||||
|
||||
~~~text
|
||||
H3 Continuum Load Session
|
||||
-> H3 Continuum Advanced.session
|
||||
-> H3 Continuum Sampler.advanced
|
||||
~~~
|
||||
|
||||
Resolution changes are rejected rather than silently resizing State or Session data.
|
||||
|
||||
## Diagnostics and debugging
|
||||
|
||||
Use **Basic** diagnostics for normal testing. Use **Detailed Report** when inspecting seam scores, selected cuts, audio correlation, correction fallback, and per-chunk context.
|
||||
|
||||
Set **debug=true** only when deeper runtime information is needed. The single-clone implementation reports object IDs without retaining the objects:
|
||||
|
||||
~~~text
|
||||
Continuum model lifetime: input=<id> chunk=<id> parent=<id> base=<id>
|
||||
~~~
|
||||
|
||||
For the expected single-clone path, every chunk parent should be the same workflow input MODEL:
|
||||
|
||||
~~~text
|
||||
chunk1.parent -> input MODEL
|
||||
chunk2.parent -> input MODEL
|
||||
chunk3.parent -> input MODEL
|
||||
~~~
|
||||
|
||||
With a compatible Spectrum version, continuation chunks should also log:
|
||||
|
||||
~~~text
|
||||
Spectrum H3: accepted H3 Continuum API v1, actual prefix=2
|
||||
~~~
|
||||
|
||||
**0 models unloaded** by itself is normal model-management information. The relevant leak warnings are:
|
||||
|
||||
~~~text
|
||||
Potential memory leak detected with model MiniMaxH3
|
||||
WARNING, memory leak with model MiniMaxH3
|
||||
~~~
|
||||
|
||||
If those warnings occur, compare identical one-chunk and two-chunk runs, then test Spectrum, Sol-Attn, and Sage individually.
|
||||
|
||||
## Special and compatibility nodes
|
||||
|
||||
The following nodes remain available for advanced workflows or saved-workflow compatibility:
|
||||
|
||||
- **H3 Continuum Sampler V2**: Legacy/Core identifier used by older V2 workflows.
|
||||
- **H3 Continuum Prompt Plan**: Explicit prompt-plan construction and inspection.
|
||||
- **H3 Continuum Save Session**
|
||||
- **H3 Continuum Load Session**
|
||||
- **H3 Continuum Session Info**
|
||||
- V1 Join, Finish, Assemble, Save State, and Load State nodes.
|
||||
|
||||
New workflows should normally use the compact **H3 Continuum Sampler** facade.
|
||||
|
||||
## Compatibility and safety
|
||||
|
||||
- Native H3 PackedLayout is preserved.
|
||||
- layout.position_ids identity is preserved when MM-RoPE coordinates are adjusted.
|
||||
- State and Session schema remain compatible.
|
||||
- V1 node identifiers remain registered.
|
||||
- Video and audio VAEs are not run between H3 chunks.
|
||||
- Full accepted chunk latents are stored on CPU.
|
||||
- SageAttention, Sol-Attn, LoRA, and Spectrum remain external packages.
|
||||
- Unknown H3 layout contracts fail clearly instead of producing a subtly incorrect continuation.
|
||||
|
||||
<!-- h3-related-projects -->
|
||||
## Related projects and implementation scope
|
||||
|
||||
| Project | Primary purpose | Workflow model | Main technical difference |
|
||||
| --- | --- | --- | --- |
|
||||
| **H3 Continuum** | Generate and assemble 1-16 H3 chunks | One integrated sampler with optional facade packs | Carries raw paired AV latent context, manages prompts/seeds/session/reroll, defers decode, and can apply post-decode seam correction. |
|
||||
| **H3 Motion Context** | Continue motion and sound from one clip into another | Explicit context, trim, and optional save/load nodes across runs | Pins prior video/audio context into the next native H3 generation and trims the repeated context from the delivered clip. |
|
||||
| **Spectrum MiniMax H3** | Reduce H3 sampling time | MODEL wrapper before the guider/sampler | Forecasts selected post-transformer hidden features. It is an approximate accelerator, not a clip-continuity system, and may change the generated result. |
|
||||
|
||||
Continuum does not copy, vendor, or bundle source code from Spectrum or H3 Motion Context. Compatibility uses ComfyUI's MODEL/payload behavior. For a supported Spectrum build, Continuum emits a small API v1 metadata hint requesting at least two actual solver steps at the start of a continuation chunk; unsupported builds ignore it and continue normally.
|
||||
|
||||
## Spectrum Actual Prefix 2 interoperability
|
||||
|
||||
Spectrum accelerates sampling by forecasting selected post-transformer hidden features from Actual H3 evaluations. A continuation chunk introduces a new AV Context and Packed Layout. Forecasting immediately after that transition could start before Spectrum has enough Actual features for the new context.
|
||||
|
||||
Continuum avoids that conflict without disabling or modifying Spectrum:
|
||||
Use approximately `0.3 MP` first when testing longer sequences or limited hardware. For a 3:2 landscape source, typical rounded sizes are approximately:
|
||||
|
||||
```text
|
||||
Stable input MODEL
|
||||
-> call-local MODEL clone for the chunk
|
||||
-> build and validate the continuation AV Context
|
||||
-> freeze the branch-specific Packed Layout signature
|
||||
-> Actual solver step 0
|
||||
-> Actual solver step 1
|
||||
-> allow the normal Spectrum forecast schedule
|
||||
0.3 MP -> 672 x 448
|
||||
0.5 MP -> 864 x 576
|
||||
0.6 MP -> 960 x 640
|
||||
```
|
||||
|
||||
- The input MODEL is not mutated; every chunk receives an isolated clone and Spectrum runtime.
|
||||
- The read-only `h3_continuum` API v1 hint is emitted only when valid previous Context exists.
|
||||
- The effective prefix is the larger of Spectrum's own warmup and Continuum's requested prefix, clamped to the configured solver-step count.
|
||||
- Context rows and generated Target rows remain separate in the native H3 Packed Layout.
|
||||
- The Packed Layout is checked per logical branch and must remain structurally stable during Native Actual calls.
|
||||
- Chunk 1 emits no hint and follows the normal Spectrum path.
|
||||
- Offline Replay reuses the recorded Actual anchors and does not apply the prefix a second time.
|
||||
- Older or unsupported Spectrum builds ignore the metadata and continue normally.
|
||||
Resolution, model precision, ComfyUI offload behavior, and other loaded nodes determine the actual memory limit.
|
||||
|
||||
Actual Prefix 2 does not add two solver steps and does not run the whole sample twice. With a 20-step schedule, the result still uses 20 solver steps. Under the standard Spectrum `warmup_steps=1` profile, it normally replaces one early forecast with one additional Actual Transformer evaluation. If the configured warmup is already two or more, it adds no evaluation.
|
||||
## Prompt formats
|
||||
|
||||
This design gives Spectrum two Context-specific Actual anchors before forecasting. It trades a small amount of the maximum possible acceleration for more stable continuation behavior.
|
||||
Connect one **Text (Multiline)** node to **Sequence Prompt**.
|
||||
|
||||
### Report output and optional Detailed Report
|
||||
- **Fixed**: one prompt is used for every chunk.
|
||||
- **List**: separate one prompt per chunk with a line containing `---`.
|
||||
- **Timeline**: use sections such as `[0-5s]`, `[5-10s]`, or `[Chunk 1]`.
|
||||
- **Auto**: detects Fixed, List, or Timeline syntax and is the recommended default.
|
||||
|
||||

|
||||
|
||||
The bundled workflow uses `Basic` reporting and leaves `H3 Continuum Result.report` unconnected. No additional report-display extension is required for the standard workflow.
|
||||
|
||||
The screenshot above is an optional troubleshooting example using `Detailed Report` and an external text display node. That display node is not included in the bundled template.
|
||||
Example List prompt:
|
||||
|
||||
```text
|
||||
Continuum report:
|
||||
interop=emitted actual_prefix=2 consumer=not_observable
|
||||
The skateboarder begins moving through the city in one continuous shot.
|
||||
---
|
||||
She continues the same motion and camera direction without a cut or reset.
|
||||
---
|
||||
She completes the action naturally while preserving identity and environment.
|
||||
```
|
||||
|
||||
Spectrum log:
|
||||
## Spectrum interoperability
|
||||
|
||||
Spectrum is optional. Continuum does not import Spectrum private runtime code.
|
||||
|
||||
When valid previous context exists, Continuum adds a small read-only API v1 hint requesting at least two Actual Transformer evaluations at the beginning of that continuation chunk. A compatible Spectrum build reports:
|
||||
|
||||
```text
|
||||
Spectrum H3: accepted H3 Continuum API v1, actual prefix=2
|
||||
```
|
||||
|
||||
`consumer=not_observable` is not an error. Interop API v1 is deliberately a one-way, read-only hint without an acknowledgement side channel. Spectrum's `accepted` log confirms that the hint was consumed.
|
||||
Actual Prefix 2 does not add solver steps. It changes the early Actual/Forecast schedule for continuation chunks. Chunk 1 emits no hint, and unsupported Spectrum versions ignore it and continue normally.
|
||||
|
||||
### Independently developed scope
|
||||
A practical accelerated starting point is:
|
||||
|
||||
The general idea of continuing one clip from another is not claimed as unique. Continuum's AV timeline validation, branch-local Packed Layout guard, call-local MODEL isolation, Spectrum Actual Prefix 2 contract, integrated multi-chunk orchestration, and seam-correction pipeline were developed independently for this project. No Spectrum or H3 Motion Context source code is copied or bundled.
|
||||
```text
|
||||
Spectrum enabled = true
|
||||
warmup_steps = 1
|
||||
tail_actual_steps = 1
|
||||
bootstrap_first_forecast = true
|
||||
offline_smoothing_replay = true
|
||||
audio_blend_weight = 0.00
|
||||
```
|
||||
|
||||
### License and external-content boundaries
|
||||
SageAttention and Spectrum remain external and optional. Sol-Attn and Turbo LoRA are not required by the current tested V3 profile.
|
||||
|
||||
- This repository is licensed under [GPL-3.0](LICENSE).
|
||||
- [Spectrum MiniMax H3](https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3/blob/main/LICENSE) is GPL-3.0.
|
||||
- [H3 Motion Context](https://github.com/NikoDemon80/ComfyUI-H3-Motion-Context/blob/main/LICENSE) is GPL-3.0.
|
||||
- The separate [ComfyUI workflow templates repository](https://github.com/Comfy-Org/workflow_templates) is MIT-licensed.
|
||||
- Model files, model cards, and other custom-node packages remain external and keep their own licenses and usage terms.
|
||||
## Current tested baseline
|
||||
|
||||
The MIT license of the template repository does not change the licenses of model weights or third-party custom nodes. This project does not redistribute MiniMax H3 weights.
|
||||
The current local V3 baseline was tested on:
|
||||
|
||||
### Tested environment
|
||||
- NVIDIA GeForce RTX 5060 Ti 16GB
|
||||
- 64GB system RAM
|
||||
- MiniMax H3 INT8 ConvRot workflow
|
||||
- SageAttention plus Spectrum
|
||||
- no Sol-Attn and no Turbo LoRA
|
||||
- `Balanced - 22 frames`
|
||||
- `Audio Seam: Off`
|
||||
|
||||
- GPU: NVIDIA GeForce RTX 5060 Ti 16GB.
|
||||
- System memory: 64GB RAM.
|
||||
- Runtime: Python 3.13.12, PyTorch 2.13.0+cu130, CUDA 13.0.
|
||||
- SageAttention: 2.2.0+cu130, using KJNodes FP8 CUDA++ with compile disabled.
|
||||
- Verified baseline environment: 3 x 5-second runs at approximately 448 x 672 (0.3 MP), using the INT8 ConvRot checkpoint and SageAttention CUDA++.
|
||||
- Bundled template profile: 3 x 5 seconds at 0.5 MP. Treat this higher-resolution profile as a starting point and monitor VRAM on the first run.
|
||||
- Longer-than-15-second chains are supported by the node design but have not yet been validated in this environment.
|
||||
- OOM avoidance is not guaranteed; peak usage depends on resolution, precision, model patches, Spectrum settings, ComfyUI offload behavior, and other loaded nodes.
|
||||
Observed long-form run:
|
||||
|
||||
```text
|
||||
6 x 5-second chunks
|
||||
672 x 448 (approximately 0.3 MP)
|
||||
24 fps / 720 frames / 30.0 seconds
|
||||
Spectrum Actual Prefix 2 accepted for chunks 2-6
|
||||
Total execution time: 12 minutes 48 seconds
|
||||
```
|
||||
|
||||
This is one validated local baseline, not a universal performance guarantee. A 60-second run and higher-resolution long-form profiles are still pending validation.
|
||||
|
||||
Development and A/B notes are available in [docs/AB_TEST_LOG_JA.md](docs/AB_TEST_LOG_JA.md).
|
||||
|
||||
## Installation
|
||||
|
||||
From the ComfyUI `custom_nodes` directory:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum.git
|
||||
```
|
||||
|
||||
Restart ComfyUI and search for:
|
||||
|
||||
```text
|
||||
H3 Continuum Sampler V3
|
||||
H3 Continuum Assemble V3
|
||||
H3 Continuum Advanced V3
|
||||
```
|
||||
|
||||
No additional Python package is required beyond a working ComfyUI MiniMax H3 environment. Model files and external accelerator nodes are not bundled.
|
||||
|
||||
If an older `ComfyUI-H3-Continuum-Join` folder exists, remove or rename it before starting ComfyUI. Do not load both package folders at the same time.
|
||||
|
||||
## Compatibility and legacy workflows
|
||||
|
||||
- Existing V1 and V2 node identifiers remain registered as Legacy nodes.
|
||||
- State, Session, and Prompt Plan schema versions remain unchanged.
|
||||
- Unknown or unsafe native H3 layout contracts fail clearly.
|
||||
- The workflow input MODEL is not mutated; each chunk uses a call-local clone.
|
||||
- Full continuation chunks are decoded before overlap trimming to preserve VAE temporal context.
|
||||
|
||||
New workflows should use the V3 sampler, ComfyUI Core VAE Decode nodes, and Assemble V3.
|
||||
|
||||
## Current limitation and roadmap
|
||||
|
||||
V3.0 keeps raw chunk latents on CPU and delegates decoding to ComfyUI Core, which substantially improves VRAM flexibility. Decoded IMAGE tensors still remain in system RAM until Assemble V3 runs, so system RAM can become the limit for very long or high-resolution output.
|
||||
|
||||
Planned work:
|
||||
|
||||
- V3.0.x: contract validation, diagnostics, and ownership/lifetime hardening without changing sampling semantics.
|
||||
- V3.1: disk-backed chunks, chunk-wise decode/release, and streaming assembly for longer sequences.
|
||||
|
||||
## Development checks
|
||||
|
||||
Use the same Python environment as ComfyUI:
|
||||
|
||||
~~~bash
|
||||
```bash
|
||||
python -m compileall -q .
|
||||
pytest -q
|
||||
~~~
|
||||
|
||||
Current local validation for this change:
|
||||
|
||||
~~~text
|
||||
74 passed
|
||||
~~~
|
||||
|
||||
GPU validation should compare identical prompts, seeds, resolutions, samplers, and sigmas across:
|
||||
|
||||
~~~text
|
||||
Native
|
||||
Sage
|
||||
Sage + Sol-Attn
|
||||
Sage + Spectrum
|
||||
Sage + Sol-Attn + Spectrum
|
||||
~~~
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
GPL-3.0-or-later. External accelerator source code is not bundled.
|
||||
GPL-3.0-or-later. External model weights and accelerator packages retain their own licenses.
|
||||
|
||||
@@ -0,0 +1,250 @@
|
||||
# H3 Continuum A/B実機テスト記録
|
||||
|
||||
更新日: 2026-08-11
|
||||
状態: 継続中。現時点の結果であり、最終推奨ではない。
|
||||
|
||||
## 1. 目的
|
||||
|
||||
H3 Continuumの3×5秒生成について、次を分離して評価する。
|
||||
|
||||
- 解像度とチャンク累積による顔・肌・Identity drift
|
||||
- Spectrumの速度向上とSeed依存のForecast誤差
|
||||
- WarmupとContinuum Actual Prefixの組み合わせ
|
||||
- Seam Correction Off/Autoの映像・音声境界への効果
|
||||
- 無音に近い条件と明確な歌唱・発話条件の違い
|
||||
|
||||
MP4本体は現時点ではGitへ追加しない。各番号はローカル出力ファイル名の末尾番号に対応する。
|
||||
|
||||
## 2. 主なテスト環境
|
||||
|
||||
```text
|
||||
GPU RTX 5060 Ti 16GB
|
||||
System RAM 64GB
|
||||
Output 640×960 / 24fps / 15秒 / 360 frames
|
||||
Image scale area / 0.60MP / resolution_steps 32
|
||||
Chunks 3
|
||||
Chunk seconds 5.0
|
||||
Continuity Balanced — 22 frames
|
||||
SageAttention sageattn_qk_int8_pv_fp8_cuda++
|
||||
Sol-Attn なし
|
||||
Audio continuity true
|
||||
Exact total duration true
|
||||
Diagnostics Basic
|
||||
```
|
||||
|
||||
Spectrum ON時の主要設定:
|
||||
|
||||
```text
|
||||
blend_weight 0.5
|
||||
degree 1
|
||||
ridge_lambda 0.1
|
||||
window_size 2.0
|
||||
flex_window 0.75
|
||||
tail_actual_steps 1
|
||||
max_history 8
|
||||
history_storage system_ram
|
||||
bootstrap_first_forecast true
|
||||
anchor_residual_feedback false
|
||||
selective_rollback_correction false
|
||||
offline_smoothing_replay true
|
||||
audio_blend_weight 0.0
|
||||
```
|
||||
|
||||
## 3. 暫定実用設定
|
||||
|
||||
品質最優先ではなく、約31%の時間短縮を取る実用バランス設定として扱う。
|
||||
|
||||
```text
|
||||
Spectrum On
|
||||
Warmup 2
|
||||
Actual Prefix 2
|
||||
Continuity Balanced 22
|
||||
Seam Off
|
||||
```
|
||||
|
||||
注意: Seed 1235でSpectrum ON時の明確な画質崩れを確認しているため、全Seedで安定する設定ではない。
|
||||
|
||||
## 4. 解像度・チャンク比較
|
||||
|
||||
| 動画 | 解像度 | 尺 | 所見 |
|
||||
|---|---:|---:|---|
|
||||
| 00032 | 448×672、約0.3MP | 15秒 | 低解像度では肌・顔の微細なdriftが目立ちにくい |
|
||||
| 00033 | 576×896、約0.5MP | 15秒 | 比較的安定 |
|
||||
| 00034 | 576×896、約0.5MP | 5秒 | 単チャンクは安定 |
|
||||
| 00035 | 640×960、約0.6MP | 5秒 | 0.6MP単独では大きな破綻なし |
|
||||
| 00036 | 640×960、約0.6MP | 15秒 | 後続チャンクほど肌の変化が見えやすい |
|
||||
|
||||
暫定解釈: 0.6MPそのものより、Continuationで小さな誤差が次チャンクへ累積し、高解像度で可視化される可能性が高い。
|
||||
|
||||
## 5. Warmup比較
|
||||
|
||||
| 動画 | Warmup | 所見 |
|
||||
|---|---:|---|
|
||||
| 00038 | 1 | プッシュインあり。境界フリックは比較的目立たない |
|
||||
| 00039 | 3 | 6秒台以降に顔の暗転・粗れが発生し、重大な破綻 |
|
||||
| 00040 | 3 | 重大破綻は再現せず、軽い肌drift。結果の振れが大きい |
|
||||
| 00041 | 2 | Seed 1234、Spectrum ON、Seam Off。全体として良好 |
|
||||
|
||||
暫定解釈:
|
||||
|
||||
- Warmup 3は結果が不安定なため不採用。
|
||||
- Warmup 2はWarmup 3より安全だが、Spectrumの全Seed安定性は保証しない。
|
||||
- Continuation chunkではActual Prefix 2が先頭2stepをActualへ要求する。
|
||||
|
||||
## 6. 厳密または準厳密なA/B比較
|
||||
|
||||
境界比は、境界の隣接フレームMAEを周辺の通常フレーム間MAE中央値で割った参考値。1未満なら境界変化が周辺動作より小さい。
|
||||
|
||||
### 6.1 Spectrum ON/OFF、Seed 1234
|
||||
|
||||
| 動画 | Spectrum | Warmup | Seam | 所見 |
|
||||
|---|---|---:|---|---|
|
||||
| 00041 | ON | 2 | Off | 良好。音声はほぼ無音、RMS約-63.7dBFS |
|
||||
| 00045 | OFF | 無効 | Off | 良好。00041と視覚的にかなり近い |
|
||||
|
||||
Seed 1234ではSpectrum ONでもNativeに近い結果を維持した。
|
||||
|
||||
### 6.2 Spectrum ON/OFF、Seed 1235
|
||||
|
||||
| 動画 | Spectrum | Warmup | Seam | 5秒比 | 10秒比 | 所見 |
|
||||
|---|---|---:|---|---:|---:|---|
|
||||
| 00042 | ON | 2 | Off | 1.392 | 1.810 | Clip 1途中で服色変化。Clip 3で顔に強い斑点と肌崩れ |
|
||||
| 00047 | OFF | 無効 | Off | 0.909 | 0.904 | 服色、肌、Identityを維持 |
|
||||
|
||||
確定事項:
|
||||
|
||||
- Seed 1235自体はNative生成で正常。
|
||||
- 00042の崩れはSpectrumとSeed 1235の組み合わせで発生した可能性が高い。
|
||||
- Seam CorrectionではClip内部のSpectrum Forecast誤差を修正できない。
|
||||
|
||||
### 6.3 Seam Auto/Off、Seed 1237
|
||||
|
||||
| 動画 | Spectrum | Warmup | Seam | 5秒比 | 10秒比 | 所見 |
|
||||
|---|---|---:|---|---:|---:|---|
|
||||
| 00044 | ON | 2 | Auto | 0.570 | 0.248 | 良好。Autoによる不自然な色変化なし |
|
||||
| 00046 | ON | 2 | Off | 0.564 | 0.333 | 良好。Auto版と視覚差は非常に小さい |
|
||||
|
||||
確定事項:
|
||||
|
||||
- 無音に近い映像ではAutoの視覚的効果は小さい。
|
||||
- Autoは10秒境界をわずかに平滑化したが、Offでも十分安定。
|
||||
- 現時点ではOffを映像品質の基準とする。
|
||||
|
||||
## 7. Seed耐性
|
||||
|
||||
| Seed | Spectrum | Warmup | Seam | 動画 | 判定 |
|
||||
|---:|---|---:|---|---|---|
|
||||
| 1234 | ON | 2 | Off | 00041 | 良好 |
|
||||
| 1234 | OFF | 無効 | Off | 00045 | 良好 |
|
||||
| 1235 | ON | 2 | Off | 00042 | 失敗 |
|
||||
| 1235 | OFF | 無効 | Off | 00047 | 良好 |
|
||||
| 1236 | ON | 2 | Auto | 00043 | 許容。カメラ動作が強い |
|
||||
| 1237 | ON | 2 | Auto | 00044 | 良好 |
|
||||
| 1237 | ON | 2 | Off | 00046 | 良好 |
|
||||
|
||||
Spectrum ONの品質はSeed依存で変化する。結果確認なしの長尺・大量生成には追加の誤差検出またはフォールバックが必要。
|
||||
|
||||
## 8. 速度比較
|
||||
|
||||
| 条件 | 動画 | 生成時間 |
|
||||
|---|---|---:|
|
||||
| Spectrum ON | 00046 | 882.52秒、約14分43秒 |
|
||||
| Spectrum OFF | 00047 | 1274.40秒、約21分14秒 |
|
||||
|
||||
```text
|
||||
短縮時間 約391.88秒、約6分32秒
|
||||
短縮率 約30.8%
|
||||
処理速度 約1.44倍
|
||||
```
|
||||
|
||||
別の比較でも約31.6%短縮しており、Spectrumの速度効果は再現している。ただし00046と00047はSeedが異なるため、この値は実用上の参考値。
|
||||
|
||||
## 9. 音声の現状
|
||||
|
||||
00041〜00047にはAAC音声ストリームがあるが、測定RMSは概ね-58〜-68dBFSで、聴感上ほぼ無音。したがって、歌唱、会話、伴奏を含むAudio ContinuityとSeam Autoの効果は未確定。
|
||||
|
||||
現時点の運用仮説:
|
||||
|
||||
```text
|
||||
映像中心・無音に近い Seam Off
|
||||
会話・歌唱・演奏あり Seam Autoの可能性。A/B未完了
|
||||
```
|
||||
|
||||
## 10. 保留中・次のテスト
|
||||
|
||||
1. Seed 1235 / Spectrum ON / Warmup 1 / Seam Off
|
||||
2. 固定カメラ・明確な持続歌唱で、同一SeedのSeam Off/Auto
|
||||
3. 歌唱と小振幅・低速プッシュインを含む実用Promptで、同一SeedのSeam Off/Auto
|
||||
4. 音声境界の前後100〜200msについて、瞬間ピーク、短時間RMS、F0、波形相関、スペクトル差、DC offsetを比較
|
||||
5. 3チャンクで安定後、5×5秒または6×5秒でIdentity driftを確認
|
||||
|
||||
## 11. 検討中の対策
|
||||
|
||||
- Clip 1だけNative計算し、Continuation chunkからSpectrumを使用
|
||||
- Spectrumの予測誤差が大きいstepだけActualへ戻す
|
||||
- selective rollback correctionとanchor residual feedbackの同一Seed A/B
|
||||
- 元画像による定期的なIdentity再アンカー
|
||||
- 異常Contextを検出し、該当チャンクだけSpectrumなしで再生成
|
||||
- Seam Autoの映像補正と音声補正を個別に選択可能にする
|
||||
|
||||
## 12. 将来のGitHub公開方法
|
||||
|
||||
- このMarkdownと機械可読なJSON/CSVを通常Gitへ追加する。
|
||||
- コンタクトシートは`docs/assets/ab-tests/`等へ追加する。
|
||||
- 大容量MP4は通常Gitへ直接追加せず、GitHub Release assetsまたはGit LFSを検討する。
|
||||
- 公開前にPrompt、Workflow、モデル、ComfyUI revision、Python/Torch/CUDA、GPU、生成時間を各サンプルへ紐付ける。
|
||||
|
||||
## 00048 / 00049: 0.5 MP Seam Off vs Auto
|
||||
|
||||
- 共通条件: 576x896 (約0.5 MP), 24 fps, 3 x 5秒, Spectrum On, Warmup 1, Actual Prefix 2, Balanced 22, base seed 1235。
|
||||
- 00048: Seam Off。5秒境界比 0.3583、10秒境界比 0.8562。
|
||||
- 00049: Seam Auto。5秒境界比 0.3709、10秒境界比 0.4271。
|
||||
- 視覚評価: 両方とも人物・衣装・肌は安定し、見た目の差は小さい。Autoは10秒境界を数値上改善した。
|
||||
- 音声: 両方ともほぼ無音のため、音声シーム効果は未評価。
|
||||
- 注意: 0.5 MP条件のため、0.6 MPで発生したSeed 1235の崩れをWarmup 1が解消したとは断定しない。
|
||||
|
||||
### 目視評価の補足
|
||||
|
||||
- ユーザー目視では00049(Seam Auto)の方がフリックが若干目立つ。
|
||||
- 00048(Seam Off)の方が境界変化を比較的抑えられている。
|
||||
- 境界指標の改善と主観的なフリック低減は一致しなかったため、本比較では目視評価を優先しSeam Offを採用候補とする。
|
||||
|
||||
|
||||
## 00050: 音声あり一貫性テスト
|
||||
|
||||
- 条件: 576x896(約0.5 MP)、24 fps、3 x 5秒、Spectrum On、Warmup 1、Balanced 22、base seed 1235、Seam Off。
|
||||
- 音声レベル: mean -19.9 dB、peak -6.4 dB。前回のほぼ無音サンプルより音声境界の評価に適する。
|
||||
- 目視: 3チャンクを通して人物、髪、衣装、背景、露出は安定。肌・顔の累積崩れも目立たない。
|
||||
- 5秒境界: 境界付近で瞬きが始まるためフレーム差はあるが、露出フリックより自然動作として見える。
|
||||
- 10秒境界: 口形、顔、背景の連続性が高く、明確な視覚ジャンプは小さい。
|
||||
- 未確認: 音声境界のクリック、F0、短時間RMS、スペクトル差の数値解析。
|
||||
- 次の比較: 同一Prompt・Seed・解像度・Warmupのまま、SeamだけAutoへ変更した1本と比較する。
|
||||
|
||||
### 00050 音声の目視・聴感補足
|
||||
|
||||
- ユーザー聴感で10秒(Chunk 2→3境界)に短いプチノイズを確認。
|
||||
- 同境界の映像連続性は良好であり、映像シームと音声シームの品質が一致しない例となった。
|
||||
- 暫定対策候補: Video Seam Off、Audio Seam Autoを独立設定にする。
|
||||
|
||||
|
||||
### 00050 実行レポート補足
|
||||
|
||||
- Prompt plan: Fixed、3 chunks、5.000秒。Seam correction Off。
|
||||
- Chunk seeds: 12362262848839836333 / 1129406137053299874 / 8524677167168820503。
|
||||
- Continuity motion: Chunk 2 = 0.378492、Chunk 3 = 0.388277。Continuation chunksはActual Prefix 2を要求。
|
||||
- Retained frames: 124 + 119 + 119 = 362。Exact-durationで360 framesへ末尾調整。
|
||||
- Audio: 480000 samples(32 kHz、15.000秒)。末尾補正 -2667 samplesは2 frames相当で、10秒境界のプチノイズ原因とは分離して扱う。
|
||||
- 判定: sample-boundary alignmentは尺を整合させているが、波形位相・振幅の連続性までは保証しない。Audio Seam Off基準として保存する。
|
||||
|
||||
### 00050 境界評価の訂正
|
||||
|
||||
- 5秒(Chunk 1→2): 映像フリックが確認できる。
|
||||
- 10秒(Chunk 2→3): 映像フリックは目立たないが、音声に短いプチノイズがある。
|
||||
- 映像と音声の問題位置は一致していないため、Video SeamとAudio Seamは独立評価・独立処理が必要。
|
||||
|
||||
### 00050 最終訂正(この評価を優先)
|
||||
|
||||
- 5秒(Chunk 1→2): 映像フリックあり。
|
||||
- 10秒(Chunk 2→3): 映像フリックは目立たない。
|
||||
- 音声: 明確なプチノイズは確認できない。先行する「10秒に音声ノイズあり」という記録は取り消し、未検出として扱う。
|
||||
- 00050はAudio Seam不具合の根拠にはせず、音声は専用テストで改めて検証する。
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
[project]
|
||||
name = H3 Continuum
|
||||
version = 2.1.7
|
||||
version = 3.0.0
|
||||
description = Integrated native MiniMax H3 long-video continuation with stable Vue UI, V1 compatibility and external SageAttention, Sol-Attn and Spectrum composition.
|
||||
|
||||
@@ -363,13 +363,24 @@ from .v2.nodes import (
|
||||
NODE_CLASS_MAPPINGS.update(V2_NODE_CLASS_MAPPINGS)
|
||||
NODE_DISPLAY_NAME_MAPPINGS.update(V2_NODE_DISPLAY_NAME_MAPPINGS)
|
||||
|
||||
# V3 keeps the V1/V2 sampling and state contracts but exposes raw AV chunks so
|
||||
# ComfyUI Core owns video/audio VAE decoding.
|
||||
from .v3.nodes import (
|
||||
NODE_CLASS_MAPPINGS as V3_NODE_CLASS_MAPPINGS,
|
||||
NODE_DISPLAY_NAME_MAPPINGS as V3_NODE_DISPLAY_NAME_MAPPINGS,
|
||||
)
|
||||
|
||||
NODE_CLASS_MAPPINGS.update(V3_NODE_CLASS_MAPPINGS)
|
||||
NODE_DISPLAY_NAME_MAPPINGS.update(V3_NODE_DISPLAY_NAME_MAPPINGS)
|
||||
|
||||
# The stable facade and its pack helpers are the public workflow surface. Keep
|
||||
# every older identifier registered so saved workflows still load, while
|
||||
# ComfyUI's native deprecated-node filter hides legacy building blocks.
|
||||
_primary_node_ids = {
|
||||
"H3ContinuumSampler",
|
||||
"H3ContinuumSamplerV3",
|
||||
"H3ContinuumAssembleV3",
|
||||
"H3ContinuumAdvancedV3",
|
||||
"H3ContinuumClipOverrides",
|
||||
"H3ContinuumAdvanced",
|
||||
"H3ContinuumResult",
|
||||
}
|
||||
for _node_id, _node_class in NODE_CLASS_MAPPINGS.items():
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "comfyui-h3-continuum"
|
||||
version = "2.1.7"
|
||||
version = "3.0.0"
|
||||
description = "Integrated N-chunk continuation for ComfyUI native MiniMax H3 video and audio"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
|
||||
@@ -303,6 +303,7 @@ class H3ContinuumSamplerV2:
|
||||
prompt_plan=None,
|
||||
sequence_prompt=None,
|
||||
show_preview=True,
|
||||
latent_only=False,
|
||||
**clip_prompt_inputs,
|
||||
):
|
||||
(
|
||||
@@ -367,6 +368,7 @@ class H3ContinuumSamplerV2:
|
||||
enable_preview=bool(show_preview),
|
||||
session=session,
|
||||
initial_state=initial_state,
|
||||
latent_only=bool(latent_only),
|
||||
)
|
||||
|
||||
|
||||
|
||||
+11
-2
@@ -75,7 +75,7 @@ def _conditioning_cache(*,clip,prompts,assets,final_has_last_frame):
|
||||
cache[key]=encode_prompt_conditioning(clip,prompt,first_image=assets.first_image,last_image=assets.last_image if include_last else None)
|
||||
return cache
|
||||
|
||||
def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,sigmas:torch.Tensor,first_frame:torch.Tensor|None,last_frame:torch.Tensor|None,prompt_plan:dict[str,Any],width:int,height:int,continuity:str,base_seed:int,audio_continuity:bool,exact_total_duration:bool,diagnostics_mode:str,reroll_from_chunk:int,reroll_nonce:int,strict_compatibility:bool,debug:bool,seam_correction:str=SEAM_CORRECTION_OFF,enable_preview:bool=True,session:dict[str,Any]|None=None,initial_state:dict[str,Any]|None=None):
|
||||
def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,sigmas:torch.Tensor,first_frame:torch.Tensor|None,last_frame:torch.Tensor|None,prompt_plan:dict[str,Any],width:int,height:int,continuity:str,base_seed:int,audio_continuity:bool,exact_total_duration:bool,diagnostics_mode:str,reroll_from_chunk:int,reroll_nonce:int,strict_compatibility:bool,debug:bool,seam_correction:str=SEAM_CORRECTION_OFF,enable_preview:bool=True,session:dict[str,Any]|None=None,initial_state:dict[str,Any]|None=None,latent_only:bool=False):
|
||||
diagnostics_mode=normalize_diagnostics_mode(diagnostics_mode); plan=validate_prompt_plan(prompt_plan); chunks=int(plan["chunks"]); chunk_seconds=float(plan["chunk_seconds"]); prompts=list(plan["prompts"]); prompt_hashes=list(plan["hashes"]); width,height=int(width),int(height)
|
||||
if width<=0 or height<=0 or width%32 or height%32: raise SequenceRuntimeError("width and height must be positive multiples of 32")
|
||||
if session is not None and initial_state is not None: raise SequenceRuntimeError("connect either a session or an initial_state, not both")
|
||||
@@ -83,7 +83,8 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
|
||||
if seam_correction not in SEAM_CORRECTION_OPTIONS: raise SequenceRuntimeError(f"unknown seam correction mode: {seam_correction!r}")
|
||||
if not 0<=int(reroll_from_chunk)<=chunks: raise SequenceRuntimeError("reroll_from_chunk must be 0 or a valid one-based chunk index")
|
||||
if initial_state is not None and int(reroll_from_chunk) not in (0,1): raise SequenceRuntimeError("with initial_state, reroll_from_chunk can only be 0 or 1")
|
||||
decode_estimate_gib,available_ram_gib=_check_decode_memory_budget(width=width,height=height,chunks=chunks,chunk_seconds=chunk_seconds)
|
||||
decode_estimate_gib=0.0; available_ram_gib=None
|
||||
if not latent_only: decode_estimate_gib,available_ram_gib=_check_decode_memory_budget(width=width,height=height,chunks=chunks,chunk_seconds=chunk_seconds)
|
||||
issues=check_comfy_h3_runtime()
|
||||
if issues and strict_compatibility: raise SequenceRuntimeError("H3 runtime is incompatible: "+"; ".join(issues))
|
||||
assets=prepare_identity_assets(video_vae,width=width,height=height,first_frame=first_frame,last_frame=last_frame,encode_latents=False)
|
||||
@@ -121,6 +122,14 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
|
||||
sampling_reports.append(f"chunk {sequence_index+1}/{chunks}: seed={seed}, frames={chunk_plan['total_frames']}, trim={chunk_plan['trim_frames']}, retained_total={retained_frames}, context={context_frames} ({reason}), motion={motion_score:.6f}, "+(f"interop=emitted actual_prefix={CONTINUUM_ACTUAL_PREFIX_STEPS} consumer=not_observable" if context_before is not None else "interop=not_emitted"))
|
||||
del sampled,latent,conditioning,chunk_model
|
||||
if len(entries)!=chunks: raise SequenceRuntimeError(f"internal sequence length mismatch: expected {chunks}, got {len(entries)}")
|
||||
if latent_only:
|
||||
last_state=entry_to_state(entries[-1]); parent_id=session.get("session_id") if session is not None else None
|
||||
settings={"continuity":continuity,"audio_continuity":bool(audio_continuity),"exact_total_duration":False,"prompt_mode":plan["mode"],"base_seed":int(base_seed),"reroll_nonce":int(reroll_nonce),"diagnostics_mode":diagnostics_mode,"initial_state_source":initial_state is not None,"latent_first":True}
|
||||
new_session=make_session(chunks=entries,width=width,height=height,chunk_seconds=chunk_seconds,identity_hash=assets.identity_hash,model_fingerprint_value=current_model_fingerprint,parent_session_id=parent_id,reroll_from_chunk=int(reroll_from_chunk),settings=settings)
|
||||
report_lines=[f"H3 Continuum V3 {PACKAGE_VERSION}",prompt_plan_report(plan),"Decode: external ComfyUI Core VAE nodes; full raw AV chunks retained.",accelerators,"Execution: conditioning precomputed; single call-local MODEL clone per chunk; no internal VAE decode.",*reuse_notes]
|
||||
if diagnostics_mode!=DIAGNOSTICS_OFF: report_lines.extend(sampling_reports)
|
||||
report_lines.extend([session_summary(new_session),f"Output: {len(entries)} raw AV latent chunk(s); connect Core VAE Decode nodes, then H3 Continuum Assemble V3."])
|
||||
return entries,last_state,new_session,"\n".join(report_lines)
|
||||
if seam_correction==SEAM_CORRECTION_OFF: images,audio,decode_reports=decode_sequence(entries=entries,video_vae=video_vae,audio_vae=audio_vae,diagnostics_full=diagnostics_mode==DIAGNOSTICS_FULL)
|
||||
else: images,audio,decode_reports=decode_sequence_with_seam(entries=entries,video_vae=video_vae,audio_vae=audio_vae,diagnostics_mode=diagnostics_mode,automatic=seam_correction==SEAM_CORRECTION_AUTO)
|
||||
duration_report=""
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Latent-first H3 Continuum V3 nodes."""
|
||||
|
||||
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
|
||||
|
||||
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|
||||
+269
@@ -0,0 +1,269 @@
|
||||
"""Decoded chunk assembly for latent-first H3 Continuum V3."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
import torch
|
||||
|
||||
from ..media import validate_audio
|
||||
from ..v2.decoder import _slice_audio_for_timeline, enforce_total_frames
|
||||
from ..constants import (
|
||||
DIAGNOSTICS_FULL,
|
||||
DIAGNOSTICS_OFF,
|
||||
DIAGNOSTICS_OPTIONS,
|
||||
normalize_diagnostics_mode,
|
||||
)
|
||||
from ..v2.seam_guard import correct_audio_seam
|
||||
from .plan import FPS, validate_assembly_plan
|
||||
|
||||
AUDIO_SEAM_OFF = "Off"
|
||||
AUDIO_SEAM_AUTO = "Auto"
|
||||
AUDIO_SEAM_OPTIONS = (AUDIO_SEAM_OFF, AUDIO_SEAM_AUTO)
|
||||
|
||||
|
||||
def _singleton(value: Any, name: str) -> Any:
|
||||
while isinstance(value, list):
|
||||
if len(value) != 1:
|
||||
raise ValueError(f"{name} must contain exactly one value")
|
||||
value = value[0]
|
||||
return value
|
||||
|
||||
|
||||
def _chunk_list(value: Any) -> list[Any]:
|
||||
if isinstance(value, list):
|
||||
if len(value) == 1 and isinstance(value[0], list):
|
||||
return list(value[0])
|
||||
return list(value)
|
||||
return [value]
|
||||
|
||||
|
||||
def assemble_decoded_chunks(
|
||||
*,
|
||||
images: list[Any],
|
||||
audio: list[Any],
|
||||
assembly_plan: dict[str, Any],
|
||||
exact_total_duration: bool,
|
||||
audio_seam: str,
|
||||
diagnostics: str,
|
||||
):
|
||||
plan = validate_assembly_plan(assembly_plan)
|
||||
diagnostics_mode = normalize_diagnostics_mode(diagnostics)
|
||||
if audio_seam not in AUDIO_SEAM_OPTIONS:
|
||||
raise ValueError(f"unknown Audio Seam mode: {audio_seam!r}")
|
||||
|
||||
chunk_plans = list(plan["chunks"])
|
||||
if len(images) != len(chunk_plans) or len(audio) != len(chunk_plans):
|
||||
raise ValueError(
|
||||
"decoded chunk count does not match the V3 assembly plan: "
|
||||
f"images={len(images)}, audio={len(audio)}, plan={len(chunk_plans)}"
|
||||
)
|
||||
|
||||
total_retained_frames = sum(int(item["net_frames"]) for item in chunk_plans)
|
||||
image_buffer = None
|
||||
audio_buffer = None
|
||||
audio_rate = None
|
||||
frame_cursor = 0
|
||||
reports = [
|
||||
"H3 Continuum Assemble V3",
|
||||
f"Audio Seam: {audio_seam}. Video seam correction is disabled.",
|
||||
]
|
||||
|
||||
for index, (raw_images, raw_audio, chunk) in enumerate(
|
||||
zip(images, audio, chunk_plans), start=1
|
||||
):
|
||||
if not torch.is_tensor(raw_images) or raw_images.ndim != 4:
|
||||
raise ValueError(f"decoded image chunk {index} must be [frames,H,W,C]")
|
||||
raw_images = raw_images.detach().to("cpu")
|
||||
total_frames = int(chunk["total_frames"])
|
||||
trim_frames = int(chunk["trim_frames"])
|
||||
net_frames = int(chunk["net_frames"])
|
||||
if int(raw_images.shape[0]) < total_frames:
|
||||
raise ValueError(
|
||||
f"decoded image chunk {index} has {raw_images.shape[0]} frames; "
|
||||
f"expected at least {total_frames}"
|
||||
)
|
||||
segment_images = raw_images[:total_frames][trim_frames:].contiguous()
|
||||
if int(segment_images.shape[0]) != net_frames:
|
||||
raise ValueError(
|
||||
f"decoded image chunk {index} retained {segment_images.shape[0]} frames; "
|
||||
f"plan expects {net_frames}"
|
||||
)
|
||||
|
||||
waveform, sample_rate = validate_audio(raw_audio)
|
||||
waveform = waveform.detach().to("cpu")
|
||||
sample_rate = int(sample_rate)
|
||||
raw_audio_cpu = {"waveform": waveform, "sample_rate": sample_rate}
|
||||
if audio_rate is None:
|
||||
audio_rate = sample_rate
|
||||
elif sample_rate != audio_rate:
|
||||
raise ValueError(
|
||||
f"audio sample rate changed between chunks: {audio_rate} -> {sample_rate}"
|
||||
)
|
||||
|
||||
frame_stop = frame_cursor + net_frames
|
||||
segment_waveform = _slice_audio_for_timeline(
|
||||
raw_audio_cpu,
|
||||
trim_frames=trim_frames,
|
||||
frame_start=frame_cursor,
|
||||
frame_stop=frame_stop,
|
||||
)
|
||||
|
||||
if image_buffer is None:
|
||||
image_buffer = torch.empty(
|
||||
(total_retained_frames, *segment_images.shape[1:]),
|
||||
dtype=segment_images.dtype,
|
||||
device="cpu",
|
||||
)
|
||||
elif tuple(segment_images.shape[1:]) != tuple(image_buffer.shape[1:]):
|
||||
raise ValueError(f"decoded image geometry changed at chunk {index}")
|
||||
image_buffer[frame_cursor:frame_stop].copy_(segment_images)
|
||||
|
||||
if audio_buffer is None:
|
||||
audio_buffer = torch.empty(
|
||||
(
|
||||
*waveform.shape[:-1],
|
||||
int(round(total_retained_frames / FPS * sample_rate)),
|
||||
),
|
||||
dtype=waveform.dtype,
|
||||
device="cpu",
|
||||
)
|
||||
elif tuple(segment_waveform.shape[:-1]) != tuple(audio_buffer.shape[:-1]):
|
||||
raise ValueError(
|
||||
"decoded audio batch/channel structure changed between chunks"
|
||||
)
|
||||
|
||||
sample_start = int(round(frame_cursor / FPS * sample_rate))
|
||||
sample_stop = int(round(frame_stop / FPS * sample_rate))
|
||||
seam_report = None
|
||||
if index > 1 and audio_seam == AUDIO_SEAM_AUTO:
|
||||
try:
|
||||
cut_sample = int(round(trim_frames / FPS * sample_rate))
|
||||
patch, metrics, fade_samples, level_gain, dc_bias = correct_audio_seam(
|
||||
audio_buffer[..., :sample_start],
|
||||
waveform,
|
||||
sample_rate=sample_rate,
|
||||
cut_sample=cut_sample,
|
||||
)
|
||||
if patch is not None and int(patch.shape[-1]) > 0:
|
||||
patch_start = sample_start - int(patch.shape[-1])
|
||||
if patch_start < 0:
|
||||
raise ValueError("audio seam patch starts before the output")
|
||||
audio_buffer[..., patch_start:sample_start].copy_(patch)
|
||||
seam_report = (
|
||||
f"audio seam {index-1}->{index}: "
|
||||
f"corr={metrics.correlation_before:.4f}->{metrics.correlation_after:.4f}, "
|
||||
f"jump={metrics.boundary_jump_before:.6f}->{metrics.boundary_jump_after:.6f}, "
|
||||
f"fade={fade_samples} samples"
|
||||
)
|
||||
if diagnostics_mode == DIAGNOSTICS_FULL:
|
||||
seam_report += (
|
||||
f", offset={metrics.offset_samples:+d}, "
|
||||
f"gain={level_gain:.4f}, dc={dc_bias:+.6f}"
|
||||
)
|
||||
except Exception as exc:
|
||||
seam_report = (
|
||||
f"audio seam {index-1}->{index}: fallback to native boundary "
|
||||
f"({type(exc).__name__}: {exc})"
|
||||
)
|
||||
|
||||
audio_buffer[..., sample_start:sample_stop].copy_(segment_waveform)
|
||||
if diagnostics_mode != DIAGNOSTICS_OFF:
|
||||
reports.append(
|
||||
f"assembled decoded chunk {index}: {net_frames} retained frames, "
|
||||
f"cumulative {frame_stop}/{total_retained_frames}"
|
||||
)
|
||||
if seam_report:
|
||||
reports.append(seam_report)
|
||||
frame_cursor = frame_stop
|
||||
|
||||
if image_buffer is None or audio_buffer is None or audio_rate is None:
|
||||
raise RuntimeError("V3 assembler failed to allocate output buffers")
|
||||
if frame_cursor != total_retained_frames:
|
||||
raise RuntimeError(
|
||||
f"V3 assembly cursor mismatch: {frame_cursor} != {total_retained_frames}"
|
||||
)
|
||||
|
||||
result_audio = {
|
||||
"waveform": audio_buffer.contiguous(),
|
||||
"sample_rate": audio_rate,
|
||||
}
|
||||
duration_report = ""
|
||||
if exact_total_duration:
|
||||
image_buffer, result_audio, duration_report = enforce_total_frames(
|
||||
image_buffer.contiguous(),
|
||||
result_audio,
|
||||
target_frames=int(plan["target_frames"]),
|
||||
preserve_final_frame=bool(plan.get("preserve_final_frame")),
|
||||
)
|
||||
|
||||
reports.append(
|
||||
f"Assembled {len(chunk_plans)} externally decoded chunks into "
|
||||
f"{image_buffer.shape[0]} frames with cumulative sample-boundary alignment."
|
||||
)
|
||||
if duration_report:
|
||||
reports.append(duration_report)
|
||||
return image_buffer.contiguous(), result_audio, "\n".join(reports)
|
||||
|
||||
|
||||
class H3ContinuumAssembleV3:
|
||||
DESCRIPTION = (
|
||||
"Assemble full AV chunks decoded by ComfyUI Core. Trims decoded context, "
|
||||
"aligns audio on cumulative frame boundaries, and optionally applies Audio Seam Auto."
|
||||
)
|
||||
SEARCH_ALIASES = ["H3 latent assemble", "H3 external VAE decode"]
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"images": ("IMAGE",),
|
||||
"audio": ("AUDIO",),
|
||||
"assembly_plan": ("H3_CONTINUUM_ASSEMBLY_PLAN",),
|
||||
"exact_total_duration": ("BOOLEAN", {"default": True}),
|
||||
"audio_seam": (
|
||||
AUDIO_SEAM_OPTIONS,
|
||||
{
|
||||
"default": AUDIO_SEAM_OFF,
|
||||
"display_name": "Audio Seam",
|
||||
"tooltip": (
|
||||
"Auto corrects only decoded audio boundaries; "
|
||||
"video frames are never altered."
|
||||
),
|
||||
},
|
||||
),
|
||||
"diagnostics": (
|
||||
DIAGNOSTICS_OPTIONS,
|
||||
{
|
||||
"default": DIAGNOSTICS_OPTIONS[0],
|
||||
"display_name": "Report Detail",
|
||||
},
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
INPUT_IS_LIST = True
|
||||
RETURN_TYPES = ("IMAGE", "AUDIO", "STRING")
|
||||
RETURN_NAMES = ("images", "audio", "report")
|
||||
FUNCTION = "assemble"
|
||||
CATEGORY = "MiniMax H3/Continuum"
|
||||
|
||||
def assemble(
|
||||
self,
|
||||
images,
|
||||
audio,
|
||||
assembly_plan,
|
||||
exact_total_duration,
|
||||
audio_seam,
|
||||
diagnostics,
|
||||
):
|
||||
return assemble_decoded_chunks(
|
||||
images=_chunk_list(images),
|
||||
audio=_chunk_list(audio),
|
||||
assembly_plan=_singleton(assembly_plan, "assembly_plan"),
|
||||
exact_total_duration=bool(
|
||||
_singleton(exact_total_duration, "exact_total_duration")
|
||||
),
|
||||
audio_seam=str(_singleton(audio_seam, "audio_seam")),
|
||||
diagnostics=str(_singleton(diagnostics, "diagnostics")),
|
||||
)
|
||||
+308
@@ -0,0 +1,308 @@
|
||||
"""Public latent-first facade nodes for H3 Continuum V3."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from ..v2.nodes import (
|
||||
CATEGORY,
|
||||
DIAGNOSTICS_OPTIONS,
|
||||
H3ContinuumSamplerV2,
|
||||
PROMPT_FORMAT_OPTIONS,
|
||||
SEAM_CORRECTION_OFF,
|
||||
SPARSE_OVERRIDE_SCHEMA_VERSION,
|
||||
V2_CONTINUITY_OPTIONS,
|
||||
validate_sparse_prompt_overrides,
|
||||
)
|
||||
from .assembly import H3ContinuumAssembleV3
|
||||
from .plan import make_assembly_plan
|
||||
|
||||
|
||||
class H3ContinuumAdvancedV3:
|
||||
DESCRIPTION = (
|
||||
"Optional continuation, session, reroll, and diagnostics settings for V3."
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"audio_continuity": ("BOOLEAN", {"default": True}),
|
||||
"diagnostics": (
|
||||
DIAGNOSTICS_OPTIONS,
|
||||
{
|
||||
"default": DIAGNOSTICS_OPTIONS[0],
|
||||
"display_name": "Report Detail",
|
||||
},
|
||||
),
|
||||
"reroll_from_chunk": (
|
||||
"INT",
|
||||
{"default": 0, "min": 0, "max": 16, "step": 1},
|
||||
),
|
||||
"reroll_nonce": (
|
||||
"INT",
|
||||
{
|
||||
"default": 0,
|
||||
"min": 0,
|
||||
"max": 0xFFFFFFFF,
|
||||
"step": 1,
|
||||
},
|
||||
),
|
||||
"strict_compatibility": ("BOOLEAN", {"default": True}),
|
||||
"debug": ("BOOLEAN", {"default": False}),
|
||||
"show_preview": ("BOOLEAN", {"default": True}),
|
||||
},
|
||||
"optional": {
|
||||
"last_frame": ("IMAGE",),
|
||||
"session": ("H3_CONTINUUM_SESSION",),
|
||||
"initial_state": ("H3_CONTINUUM_STATE",),
|
||||
"prompt_plan": ("H3_CONTINUUM_PROMPT_PLAN",),
|
||||
},
|
||||
}
|
||||
|
||||
RETURN_TYPES = ("H3_CONTINUUM_ADVANCED_V3",)
|
||||
RETURN_NAMES = ("advanced",)
|
||||
FUNCTION = "pack"
|
||||
CATEGORY = CATEGORY
|
||||
|
||||
def pack(
|
||||
self,
|
||||
audio_continuity,
|
||||
diagnostics,
|
||||
reroll_from_chunk,
|
||||
reroll_nonce,
|
||||
strict_compatibility,
|
||||
debug,
|
||||
show_preview,
|
||||
last_frame=None,
|
||||
session=None,
|
||||
initial_state=None,
|
||||
prompt_plan=None,
|
||||
):
|
||||
return (
|
||||
{
|
||||
"audio_continuity": bool(audio_continuity),
|
||||
"diagnostics": diagnostics,
|
||||
"reroll_from_chunk": int(reroll_from_chunk),
|
||||
"reroll_nonce": int(reroll_nonce),
|
||||
"strict_compatibility": bool(strict_compatibility),
|
||||
"debug": bool(debug),
|
||||
"show_preview": bool(show_preview),
|
||||
"last_frame": last_frame,
|
||||
"session": session,
|
||||
"initial_state": initial_state,
|
||||
"prompt_plan": prompt_plan,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
class H3ContinuumSamplerV3:
|
||||
DESCRIPTION = (
|
||||
"Latent-first N-chunk MiniMax H3 sampler. Sampling, native continuation, "
|
||||
"State/Session, and Spectrum interop stay inside Continuum; ComfyUI Core "
|
||||
"performs video and audio VAE decoding."
|
||||
)
|
||||
SEARCH_ALIASES = [
|
||||
"H3 Continuum V3",
|
||||
"H3 latent first",
|
||||
"MiniMax H3 external VAE decode",
|
||||
]
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {
|
||||
"required": {
|
||||
"model": ("MODEL",),
|
||||
"clip": ("CLIP",),
|
||||
"video_vae": (
|
||||
"VAE",
|
||||
{
|
||||
"tooltip": (
|
||||
"Used only to encode first/last-frame conditioning; "
|
||||
"V3 never decodes with it."
|
||||
),
|
||||
},
|
||||
),
|
||||
"sampler": ("SAMPLER",),
|
||||
"sigmas": ("SIGMAS",),
|
||||
"sequence_prompt": (
|
||||
"STRING",
|
||||
{
|
||||
"forceInput": True,
|
||||
"display_name": "Sequence Prompt",
|
||||
"tooltip": (
|
||||
"Connect one Text (Multiline) for the complete sequence."
|
||||
),
|
||||
},
|
||||
),
|
||||
"prompt_mode": (
|
||||
PROMPT_FORMAT_OPTIONS,
|
||||
{
|
||||
"default": PROMPT_FORMAT_OPTIONS[0],
|
||||
"display_name": "Prompt Format",
|
||||
},
|
||||
),
|
||||
"chunks": ("INT", {"default": 3, "min": 1, "max": 16, "step": 1}),
|
||||
"chunk_seconds": (
|
||||
"FLOAT",
|
||||
{"default": 5.0, "min": 4.0, "max": 15.0, "step": 0.1},
|
||||
),
|
||||
"width": (
|
||||
"INT",
|
||||
{"default": 1344, "min": 32, "max": 16384, "step": 32},
|
||||
),
|
||||
"height": (
|
||||
"INT",
|
||||
{"default": 768, "min": 32, "max": 16384, "step": 32},
|
||||
),
|
||||
"continuity": (
|
||||
V2_CONTINUITY_OPTIONS,
|
||||
{"default": V2_CONTINUITY_OPTIONS[1]},
|
||||
),
|
||||
"base_seed": (
|
||||
"INT",
|
||||
{
|
||||
"default": 0,
|
||||
"min": 0,
|
||||
"max": 0xFFFFFFFFFFFFFFFF,
|
||||
"control_after_generate": True,
|
||||
},
|
||||
),
|
||||
},
|
||||
"optional": {
|
||||
"first_frame": ("IMAGE",),
|
||||
"prompt_overrides": ("H3_CONTINUUM_CLIP_OVERRIDES",),
|
||||
"advanced": ("H3_CONTINUUM_ADVANCED_V3",),
|
||||
},
|
||||
}
|
||||
|
||||
RETURN_TYPES = (
|
||||
"LATENT",
|
||||
"LATENT",
|
||||
"H3_CONTINUUM_ASSEMBLY_PLAN",
|
||||
"H3_CONTINUUM_RESULT",
|
||||
)
|
||||
RETURN_NAMES = (
|
||||
"video_latents",
|
||||
"audio_latents",
|
||||
"assembly_plan",
|
||||
"result",
|
||||
)
|
||||
OUTPUT_IS_LIST = (True, True, False, False)
|
||||
FUNCTION = "run"
|
||||
CATEGORY = CATEGORY
|
||||
|
||||
def run(
|
||||
self,
|
||||
model,
|
||||
clip,
|
||||
video_vae,
|
||||
sampler,
|
||||
sigmas,
|
||||
sequence_prompt,
|
||||
prompt_mode,
|
||||
chunks,
|
||||
chunk_seconds,
|
||||
width,
|
||||
height,
|
||||
continuity,
|
||||
base_seed,
|
||||
first_frame=None,
|
||||
prompt_overrides=None,
|
||||
advanced=None,
|
||||
):
|
||||
if prompt_overrides is not None and not isinstance(prompt_overrides, dict):
|
||||
raise TypeError(
|
||||
"prompt_overrides must be an H3_CONTINUUM_CLIP_OVERRIDES pack"
|
||||
)
|
||||
if advanced is not None and not isinstance(advanced, dict):
|
||||
raise TypeError("advanced must be an H3_CONTINUUM_ADVANCED_V3 pack")
|
||||
|
||||
advanced_values = {
|
||||
"audio_continuity": True,
|
||||
"diagnostics": DIAGNOSTICS_OPTIONS[0],
|
||||
"reroll_from_chunk": 0,
|
||||
"reroll_nonce": 0,
|
||||
"strict_compatibility": True,
|
||||
"debug": False,
|
||||
"show_preview": True,
|
||||
"last_frame": None,
|
||||
"session": None,
|
||||
"initial_state": None,
|
||||
"prompt_plan": None,
|
||||
}
|
||||
if advanced:
|
||||
advanced_values.update(advanced)
|
||||
|
||||
clip_prompt_inputs = {}
|
||||
if prompt_overrides:
|
||||
if (
|
||||
type(prompt_overrides.get("schema_version")) is not int
|
||||
or prompt_overrides.get("schema_version")
|
||||
!= SPARSE_OVERRIDE_SCHEMA_VERSION
|
||||
):
|
||||
raise ValueError("unsupported H3_CONTINUUM_CLIP_OVERRIDES schema")
|
||||
sparse_overrides = validate_sparse_prompt_overrides(
|
||||
prompt_overrides.get("overrides"), chunks=int(chunks)
|
||||
)
|
||||
for index, prompt in sparse_overrides.items():
|
||||
clip_prompt_inputs[f"clip_{index}_prompt"] = prompt
|
||||
|
||||
entries, last_state, session, report = H3ContinuumSamplerV2().run(
|
||||
model=model,
|
||||
clip=clip,
|
||||
video_vae=video_vae,
|
||||
audio_vae=None,
|
||||
sampler=sampler,
|
||||
sigmas=sigmas,
|
||||
prompt_mode=prompt_mode,
|
||||
prompt_script=sequence_prompt,
|
||||
chunks=chunks,
|
||||
chunk_seconds=chunk_seconds,
|
||||
width=width,
|
||||
height=height,
|
||||
continuity=continuity,
|
||||
base_seed=base_seed,
|
||||
audio_continuity=advanced_values["audio_continuity"],
|
||||
exact_total_duration=False,
|
||||
diagnostics=advanced_values["diagnostics"],
|
||||
reroll_from_chunk=advanced_values["reroll_from_chunk"],
|
||||
reroll_nonce=advanced_values["reroll_nonce"],
|
||||
strict_compatibility=advanced_values["strict_compatibility"],
|
||||
debug=advanced_values["debug"],
|
||||
seam_correction=SEAM_CORRECTION_OFF,
|
||||
first_frame=first_frame,
|
||||
last_frame=advanced_values["last_frame"],
|
||||
session=advanced_values["session"],
|
||||
initial_state=advanced_values["initial_state"],
|
||||
prompt_plan=advanced_values["prompt_plan"],
|
||||
sequence_prompt=sequence_prompt,
|
||||
show_preview=advanced_values["show_preview"],
|
||||
latent_only=True,
|
||||
**clip_prompt_inputs,
|
||||
)
|
||||
|
||||
assembly_plan = make_assembly_plan(
|
||||
entries,
|
||||
chunk_seconds=float(chunk_seconds),
|
||||
preserve_final_frame=advanced_values["last_frame"] is not None,
|
||||
)
|
||||
video_latents = [{"samples": entry["video"]} for entry in entries]
|
||||
audio_latents = [{"samples": entry["audio"]} for entry in entries]
|
||||
result = {
|
||||
"last_state": last_state,
|
||||
"session": session,
|
||||
"report": report,
|
||||
}
|
||||
return video_latents, audio_latents, assembly_plan, result
|
||||
|
||||
|
||||
NODE_CLASS_MAPPINGS = {
|
||||
"H3ContinuumSamplerV3": H3ContinuumSamplerV3,
|
||||
"H3ContinuumAdvancedV3": H3ContinuumAdvancedV3,
|
||||
"H3ContinuumAssembleV3": H3ContinuumAssembleV3,
|
||||
}
|
||||
|
||||
NODE_DISPLAY_NAME_MAPPINGS = {
|
||||
"H3ContinuumSamplerV3": "H3 Continuum Sampler V3",
|
||||
"H3ContinuumAdvancedV3": "H3 Continuum Advanced V3",
|
||||
"H3ContinuumAssembleV3": "H3 Continuum Assemble V3",
|
||||
}
|
||||
+122
@@ -0,0 +1,122 @@
|
||||
"""Assembly-plan contract for latent-first H3 Continuum V3."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
import torch
|
||||
|
||||
from ..state import validate_plan
|
||||
|
||||
ASSEMBLY_PLAN_MAGIC = "H3_CONTINUUM_ASSEMBLY_PLAN"
|
||||
ASSEMBLY_PLAN_SCHEMA_VERSION = 1
|
||||
FPS = 24
|
||||
|
||||
|
||||
class AssemblyPlanError(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
def make_assembly_plan(
|
||||
entries: list[dict[str, Any]],
|
||||
*,
|
||||
chunk_seconds: float,
|
||||
preserve_final_frame: bool,
|
||||
) -> dict[str, Any]:
|
||||
if not entries:
|
||||
raise AssemblyPlanError("cannot create an assembly plan for an empty sequence")
|
||||
|
||||
chunks: list[dict[str, Any]] = []
|
||||
width = height = None
|
||||
for sequence_index, entry in enumerate(entries, start=1):
|
||||
if not isinstance(entry, dict):
|
||||
raise AssemblyPlanError(f"chunk {sequence_index} entry is not a dictionary")
|
||||
plan = validate_plan(entry.get("plan"))
|
||||
video = entry.get("video")
|
||||
audio = entry.get("audio")
|
||||
if not torch.is_tensor(video) or video.ndim < 3:
|
||||
raise AssemblyPlanError(f"chunk {sequence_index} video latent is invalid")
|
||||
if not torch.is_tensor(audio) or audio.ndim < 3:
|
||||
raise AssemblyPlanError(f"chunk {sequence_index} audio latent is invalid")
|
||||
|
||||
plan_width = int(plan["width"])
|
||||
plan_height = int(plan["height"])
|
||||
if width is None:
|
||||
width, height = plan_width, plan_height
|
||||
elif (plan_width, plan_height) != (width, height):
|
||||
raise AssemblyPlanError("chunk dimensions changed within the sequence")
|
||||
|
||||
chunks.append(
|
||||
{
|
||||
"sequence_index": sequence_index,
|
||||
"chunk_index": int(plan["clip_index"]),
|
||||
"total_frames": int(plan["total_frames"]),
|
||||
"trim_frames": int(plan["trim_frames"]),
|
||||
"net_frames": int(plan["net_frames"]),
|
||||
"context_frames": int(plan["context_frames"]),
|
||||
"expected_video_latent_t": int(video.shape[2]),
|
||||
"expected_audio_latent_t": int(audio.shape[2]),
|
||||
}
|
||||
)
|
||||
|
||||
result = {
|
||||
"magic": ASSEMBLY_PLAN_MAGIC,
|
||||
"schema_version": ASSEMBLY_PLAN_SCHEMA_VERSION,
|
||||
"fps": FPS,
|
||||
"width": int(width),
|
||||
"height": int(height),
|
||||
"chunk_seconds": float(chunk_seconds),
|
||||
"target_frames": int(round(len(chunks) * float(chunk_seconds) * FPS)),
|
||||
"preserve_final_frame": bool(preserve_final_frame),
|
||||
"chunks": chunks,
|
||||
}
|
||||
return validate_assembly_plan(result)
|
||||
|
||||
|
||||
def validate_assembly_plan(plan: Any) -> dict[str, Any]:
|
||||
if not isinstance(plan, dict) or plan.get("magic") != ASSEMBLY_PLAN_MAGIC:
|
||||
raise AssemblyPlanError("invalid H3 Continuum V3 assembly plan")
|
||||
if (
|
||||
type(plan.get("schema_version")) is not int
|
||||
or plan["schema_version"] != ASSEMBLY_PLAN_SCHEMA_VERSION
|
||||
):
|
||||
raise AssemblyPlanError(
|
||||
f"unsupported assembly plan schema {plan.get('schema_version')!r}"
|
||||
)
|
||||
if int(plan.get("fps", 0)) != FPS:
|
||||
raise AssemblyPlanError("assembly plan FPS must be 24")
|
||||
if int(plan.get("width", 0)) <= 0 or int(plan.get("height", 0)) <= 0:
|
||||
raise AssemblyPlanError("assembly plan dimensions are invalid")
|
||||
if float(plan.get("chunk_seconds", 0.0)) <= 0:
|
||||
raise AssemblyPlanError("assembly plan chunk duration is invalid")
|
||||
if int(plan.get("target_frames", 0)) <= 0:
|
||||
raise AssemblyPlanError("assembly plan target frame count is invalid")
|
||||
|
||||
chunks = plan.get("chunks")
|
||||
if not isinstance(chunks, list) or not chunks:
|
||||
raise AssemblyPlanError("assembly plan contains no chunks")
|
||||
for expected_index, chunk in enumerate(chunks, start=1):
|
||||
if not isinstance(chunk, dict):
|
||||
raise AssemblyPlanError(f"assembly chunk {expected_index} is invalid")
|
||||
if int(chunk.get("sequence_index", 0)) != expected_index:
|
||||
raise AssemblyPlanError("assembly chunk order is not contiguous")
|
||||
total = int(chunk.get("total_frames", 0))
|
||||
trim = int(chunk.get("trim_frames", -1))
|
||||
net = int(chunk.get("net_frames", 0))
|
||||
if total <= 0 or trim < 0 or net <= 0 or total - trim != net:
|
||||
raise AssemblyPlanError(
|
||||
f"assembly chunk {expected_index} frame plan is invalid"
|
||||
)
|
||||
if int(chunk.get("context_frames", -1)) < 0:
|
||||
raise AssemblyPlanError(
|
||||
f"assembly chunk {expected_index} context is invalid"
|
||||
)
|
||||
if int(chunk.get("expected_video_latent_t", 0)) <= 0:
|
||||
raise AssemblyPlanError(
|
||||
f"assembly chunk {expected_index} video latent length is invalid"
|
||||
)
|
||||
if int(chunk.get("expected_audio_latent_t", 0)) <= 0:
|
||||
raise AssemblyPlanError(
|
||||
f"assembly chunk {expected_index} audio latent length is invalid"
|
||||
)
|
||||
return plan
|
||||
+2
-2
@@ -1,8 +1,8 @@
|
||||
"""Package version and public schema identifiers."""
|
||||
|
||||
PACKAGE_VERSION = "2.1.7"
|
||||
PACKAGE_VERSION = "3.0.0"
|
||||
STATE_SCHEMA_VERSION = 1
|
||||
PLAN_SCHEMA_VERSION = 1
|
||||
PUBLIC_API_VERSION = 2
|
||||
PUBLIC_API_VERSION = 3
|
||||
SESSION_SCHEMA_VERSION = 1
|
||||
PROMPT_PLAN_SCHEMA_VERSION = 1
|
||||
|
||||
Reference in New Issue
Block a user