307 lines
18 KiB
Markdown
307 lines
18 KiB
Markdown
# ComfyUI-H3-Continuum 3.9.10 — V3.9
|
||
|
||
Generate long-form MiniMax H3 video and audio in chunks, review each result,
|
||
retry a section, and continue from compatible saved Takes.
|
||
**V3.9 is the current workflow; V3.8X2 remains available separately.**
|
||
|
||
[Download v3.9.10](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/releases/download/v3.9.10/ComfyUI-H3-Continuum-v3.9.10.zip) ·
|
||
[Release notes](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/releases/tag/v3.9.10) ·
|
||
[Checksums](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/releases/download/v3.9.10/SHA256SUMS.txt) ·
|
||
[日本語](README_JA.md)
|
||
|
||
## 3.9.10 — Spectrum reuse and Reference assignments
|
||
|
||
Fix false Sampling v6 read-only caused by Spectrum source CRLF line endings,
|
||
and add separate audited Python 3.12 profiles for the two supported Spectrum
|
||
implementations. Existing Python 3.13 profiles and valid Take identities stay exact.
|
||
Unknown code or runtime state remains non-reusable.
|
||
|
||
With external Chunks inputs, the V3.9 Reference Images table shows an assignment
|
||
range of 1–16 instead of a stale widget count. This does not change the number
|
||
of generated chunks or expand saved selections automatically.
|
||
|
||
CPU/JS: **2,096 passed / 2 skipped / 2 known expected failures**. Separate
|
||
Python 3.12 component, storage and actual-JS checks passed. Reference table
|
||
browser acceptance passed. **No new GPU acceptance is claimed for 3.9.10.**
|
||
|
||
Restart ComfyUI and refresh the browser after updating. Keep existing workflows
|
||
and Takes. Start a new Run for a newly supported configuration; old unsafe/v5
|
||
Takes remain readable and are not automatically made reusable.
|
||
[Release notes and limits](docs/RELEASE_NOTES_V3910.md).
|
||
|
||
## 3.9.9 — KJ Preview Override / Review continuation
|
||
|
||
Fix new-Run v6 read-only with the separately audited upstream KJ profile, and
|
||
show saved reasons when reuse is unavailable. Keep the original local profile,
|
||
Sampling v6 guards, old Takes and official workflow bytes.
|
||
|
||
CPU: **2,075 passed / 2 skipped / 2 known expected failures**, plus overlapping
|
||
90-case JS coverage. Upstream KJ GPU and normal-ComfyUI browser Continue both
|
||
passed: **Chunk 1 preserved, Chunk 2 generated, one reused / one new**; all four
|
||
AV outputs fully decoded. Browser checks used the existing local KJ profile.
|
||
These are targeted repair checks, not general quality or all-provider acceptance.
|
||
|
||
Restart ComfyUI and hard-refresh after updating. On Preview Override, disconnect
|
||
optional VAE/Audio VAE and set Tiny VAE `none`; retain generation VAEs. Correct
|
||
unsupported settings before starting a new Run. Old unsafe/v5 Takes remain
|
||
readable and are not automatically made reusable. No workflow rewiring or Take
|
||
deletion is required. [Full release notes](docs/RELEASE_NOTES_V399.md).
|
||
|
||
## Getting started video
|
||
|
||
[Watch: H3 Continuum V3.9 — Chunks, Prompts & Reference Images](https://youtu.be/AKJxBXaiG6Q) — **12:26**, with English narration, subtitles and chapters.
|
||
|
||
The video covers First Image setup, chunk settings, Review/Take retries,
|
||
Timeline prompts and Reference Images. For screenshots and every control,
|
||
open the [illustrated user guide](docs/USER_GUIDE.md).
|
||
|
||
## Install or update
|
||
|
||
Use one Continuum installation in `ComfyUI/custom_nodes`.
|
||
Models and third-party custom nodes are not bundled.
|
||
|
||
### Fixed-version ZIP
|
||
|
||
1. Download the **custom-node ZIP** above and optionally verify its checksum.
|
||
2. Extract its package folder into `ComfyUI/custom_nodes`.
|
||
When updating, replace the existing package; do not leave duplicate copies.
|
||
3. Restart ComfyUI and hard-refresh the browser (**Ctrl+F5**).
|
||
4. Open a V3.9 workflow below and select your installed models and input files.
|
||
|
||
Keep your saved workflows, Run/Take folders and settings when updating.
|
||
**Workflow ZIPs contain graphs, not the custom-node installer.**
|
||
|
||
### Git or ComfyUI-Manager
|
||
|
||
For a new Git installation:
|
||
|
||
```bash
|
||
cd ComfyUI/custom_nodes
|
||
git clone https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum.git
|
||
```
|
||
|
||
For an existing Git installation:
|
||
|
||
```bash
|
||
cd ComfyUI/custom_nodes/ComfyUI-H3-Continuum
|
||
git pull --ff-only origin main
|
||
```
|
||
|
||
If Manager owns your installation, update that copy through Manager.
|
||
Restart ComfyUI and refresh the browser after updating.
|
||
Registry review, Manager's selected version and GitHub Releases are separate;
|
||
the fixed-version links above identify the exact v3.9.9 package.
|
||
|
||
The package declares Python **3.10+** and ComfyUI **0.32.0+**.
|
||
The minimum declaration is not a GPU acceptance result for every Core version.
|
||
|
||
## Required model files and extensions
|
||
|
||
Download the weights separately from [Comfy-Org / MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3).
|
||
The table follows the **saved V3.9 template selections**; folders are relative to `ComfyUI/`.
|
||
|
||
| Component | File / download | Folder |
|
||
| --- | --- | --- |
|
||
| H3 diffusion model | [minimax_h3_fl2va_pruned_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors) | `models/diffusion_models/` |
|
||
| Text encoder | [qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors) | `models/text_encoders/` |
|
||
| Video VAE | [minimax_h3_video_vae_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_int8_convrot.safetensors) | `models/vae/` |
|
||
| Audio VAE | [minimax_h3_audio_vae_fp32.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors) | `models/vae/` |
|
||
|
||
Select the downloaded files in the loaders; set the text encoder's type to `minimax`.
|
||
Reselect paths if the saved `minimax/` subfolder differs from your installation.
|
||
The Video VAE loader selects INT8, although its older embedded download metadata names FP16;
|
||
choose the VAE you actually installed. [Other model variants](https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/diffusion_models) must match the generation task and loader support.
|
||
Quantized variants require compatible Core/GPU support; these selections are not a universal hardware guarantee.
|
||
The retained V3.8X2 graph instead saves DasiwaMinimaxH3_dasiwaHybridV2_int8.safetensors and
|
||
[FP16 Video VAE](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors).
|
||
That custom model is not bundled or supplied by the table above; reselect a compatible H3 model you have installed.
|
||
|
||
The complete supplied graph also needs these external node packages:
|
||
|
||
- [Spectrum](https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3) — optional acceleration; saved disabled. Its presence does not imply every version is reuse-compatible; see the compatibility table below.
|
||
- [KJNodes](https://github.com/kijai/ComfyUI-KJNodes) — supplies the template's H3 SageAttention patch. Follow its attention dependency requirements, or replace/bypass that patch if unavailable.
|
||
- [rgthree-comfy](https://github.com/rgthree/rgthree-comfy) — supplies `Power Lora Loader (rgthree)`.
|
||
|
||
**Optional Turbo:** download one task-matched [LightX2V Turbo LoRA](https://huggingface.co/lightx2v/Minimax-h3-Turbo) into `models/loras/`; the standard workflows start with all entries disabled. The separate Turbo Sample enables one LoRA.
|
||
Follow that LoRA's sampler/step instructions; [listed files and setup](docs/USER_GUIDE.md#turbo-lora-and-spectrum-in-supplied-workflows) explain the choices. Models and extensions are not installed by Continuum.
|
||
|
||
## Choose a workflow
|
||
|
||
| Workflow | Download | Use |
|
||
| --- | --- | --- |
|
||
| **V3.9** | [JSON](examples/workflows/MiniMax_H3_Continuum_V39.json) / [ZIP](examples/workflows/MiniMax_H3_Continuum_V39.zip) | Current Sampler and fixed Reference Image slots |
|
||
| **V3.9 Turbo Sample** | [JSON](examples/workflows/MiniMax_H3_Continuum_V39_Turbo_Sample.json) / [ZIP](examples/workflows/MiniMax_H3_Continuum_V39_Turbo_Sample.zip) | Auto, 2 x 8s dance and Thai rap; [setup and limits](docs/TURBO_SAMPLE.md) |
|
||
| **V3.8X2** | [JSON](examples/workflows/MiniMax_H3_Continuum_V38X2.json) / [combined ZIP](examples/workflows/MiniMax_H3_Continuum_V38X2.zip) | Retained workflow; combined ZIP also contains V3.9 |
|
||
|
||
They are also available in **Templates → ComfyUI-H3-Continuum**.
|
||
V3.8X2 graphs and their Reference wiring are not automatically converted to V3.9.
|
||
Keep the original graph and open the dedicated V3.9 graph for new work.
|
||
|
||
The templates reference external Spectrum, rgthree and KJNodes nodes.
|
||
Install, replace or remove missing optional dependencies before Queue.
|
||
In the standard workflows, Spectrum and Turbo LoRA entries are saved disabled; ComfyUI-Easy-Use is not required.
|
||
|
||
In the V3.9 template, select your own **First Image** file before Queue.
|
||
Reference loaders 1–6 start bypassed and all per-chunk assignments start off.
|
||
Slots 7–9 require you to add and connect loaders.
|
||
See [template setup and screenshots](docs/USER_GUIDE.md#start-here-v39-and-the-retained-v38x2-workflow).
|
||
|
||
## First generation
|
||
|
||
Start with a small two-chunk test before a long sequence.
|
||
|
||
1. Select your H3 model, text encoder, sampler and appropriate VAE files.
|
||
2. Write `Sequence Prompt`; use `Prompt Format = Fixed` for one shared prompt.
|
||
3. For image-to-video, use `Size Source = First Image` and choose a resolution.
|
||
The template starts at **Draft — 0.30 MP**. For exact Width/Height, use `Manual`.
|
||
4. Set `Chunks` to **2**, `Seconds per Chunk` to **5**, and check `Total Length` = **10 seconds**.
|
||
5. Keep `Base Seed` unchanged and `Control After Generate` set to `fixed`.
|
||
6. Set `Run` to `Review Each Chunk` and `Progress` to `On — Resume and Takes available`.
|
||
7. Leave `Regenerate From = Auto`, read `Ready to Queue`, then press ComfyUI's top-right **Run** button.
|
||
|
||
`Chunks` is the final target count, not the number to add on the next Queue.
|
||
Review normally generates one review unit at a time: the first output in this
|
||
example is **5 seconds**, even though the target is 10 seconds.
|
||
With Last Image terminal merging, the final two logical chunks may form one unit.
|
||
|
||
For uninterrupted generation, select `Generate Full Video` instead.
|
||
Keep Progress on if you want saved Takes, compatible resume and later regeneration.
|
||
|
||
## Review, continue and retry
|
||
|
||
Selecting a Review action does not start sampling. Select it, then press
|
||
ComfyUI's **Run** button (`Queue`) to execute it.
|
||
|
||
| Action | Next Queue |
|
||
| --- | --- |
|
||
| `Use it and continue` | Keep accepted chunks and generate the next review unit |
|
||
| `Try this chunk again` | Keep earlier chunks and create another Take of the reviewed unit |
|
||
| `Use it and finish the rest` | Keep accepted chunks and generate all remaining units |
|
||
| `Back to Settings` / `Return to Review` | Navigate between settings and review; neither queues work nor deletes Takes |
|
||
| `Use This Take` | Select a stored result without new sampling; decoding/saving may still run |
|
||
| `Continue From Here` | Branch from the selected Take and generate the next review unit |
|
||
|
||
For the **2 × 5-second** example, continue after Chunk 1 to reuse it and generate
|
||
Chunk 2; the completed result is **10 seconds**.
|
||
At completion, retrying the current unit creates another Chunk 2 Take.
|
||
|
||
Keep the same model/LoRAs, seed, prompts, media, dimensions, sampling schedule,
|
||
continuation settings and Run identity while continuing.
|
||
Keeping only the seed fixed is insufficient to guarantee reuse.
|
||
Read the status/reuse counts before treating a result as a successful continuation.
|
||
|
||
To extend a completed sequence, keep those conditions and `Regenerate From = Auto`,
|
||
increase the final `Chunks` target, and Queue again.
|
||
[Illustrated Review, Take and extension steps](docs/USER_GUIDE.md#review-continue-and-revise-a-chunked-video).
|
||
|
||
## Regenerate from a chosen chunk
|
||
|
||
1. Open settings and choose **Regenerate From = Chunk N**.
|
||
2. Keep Progress on and earlier-chunk generation inputs unchanged.
|
||
3. Choose `Generate Full Video` to rebuild N through the target in one Queue,
|
||
or `Review Each Chunk` to pause after the next review unit.
|
||
4. Set **Variation Nonce** and press ComfyUI's **Run** button.
|
||
5. Restore `Regenerate From = Auto` before ordinary continuation or Take actions.
|
||
|
||
Nonce **0** requests another automatic variation after a completed regeneration;
|
||
a compatible interrupted regeneration resumes its existing variation.
|
||
A positive Nonce fixes that variation: repeating it with identical inputs does
|
||
not request a new result. Review retry manages its own variation separately.
|
||
|
||
Earlier compatible chunks and previous Takes are retained.
|
||
Later chunks follow the changed continuation, so Full Run from Chunk 2 may
|
||
regenerate more than Chunk 2 when the target contains additional chunks.
|
||
Terminal-merged pairs are atomic; arbitrary frames inside a chunk cannot be edited.
|
||
[Regeneration details and compatibility](docs/REGENERATE_INTENT_V396.md).
|
||
|
||
## Prompts and Reference Images
|
||
|
||
- **Fixed:** one shared prompt; **List:** per-chunk prompts; **Timeline:** time-based instructions.
|
||
- V3.9 Reference Images uses fixed **Image 1–9** slots and one Sampler connection.
|
||
`All chunks` shares connected images; `Per chunk` lets you tick assignments.
|
||
- `@R1` always means Image 1, even if other slots are empty. Use tags only for
|
||
active References; resolved picture numbers can differ by physical group.
|
||
- First/Last Image, Reference Images, Reference Audio and Driving Audio have
|
||
different roles. Driving Audio preserves a source track; Reference Audio conditions generation.
|
||
- For a Reference-only test, turn First/Last Image off and choose Manual size.
|
||
A terminal-merged final pair needs the same effective Reference set in both chunks.
|
||
- Pre-resize large source images: conditioning resize does not eliminate
|
||
source-loading RAM use. A subject may persist through video continuity after its assignment ends.
|
||
|
||
[Reference guide](docs/V39_REFERENCE_INLINE.md) ·
|
||
[Prompt examples](docs/README_HISTORY.md#prompt-formats) ·
|
||
[V3.9 prompt skill](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/tree/main/write-h3-v39-reference-prompts) ·
|
||
[General prompt resources](docs/USER_GUIDE.md#prompt-and-skill-downloads)
|
||
|
||
## Storage, decoding and Second Pass
|
||
|
||
Progress saves Run/Take data for compatible reuse. The optional **Decode Cache
|
||
Helper** caches decoded results; it is separate from saved sampling history.
|
||
Finalize assembles the output; downstream Core nodes create and save the video.
|
||
|
||
Set scratch storage under **Settings → H3Continuum → Storage → Manage temporary storage**.
|
||
The folder is on the ComfyUI server and applies to Finalize and Decode Cache.
|
||
It does not move saved Runs/Takes or finished videos.
|
||
Change or clean it only with empty running/pending queues.
|
||
Moving folders on one physical drive does not reduce that drive's writes.
|
||
[Storage modes, cleanup and limits](docs/TEMPORARY_STORAGE_JA.md).
|
||
|
||
**Second Pass** is an optional bridge for external refinement/upscaling.
|
||
It is separate from chunk continuation and ordinary Review retries.
|
||
The V3.8X2 standard workflow does not require Hi-Res Fix.
|
||
V3.8 Second Pass does not support partial Review sequences; V3.9 can inherit
|
||
validated conditioning for its actual output groups.
|
||
[Integration contract](docs/V38_OPEN_INTEGRATION_CONTRACT.md).
|
||
|
||
## Compatibility and v3.9.9 scope
|
||
|
||
| Area | Supported boundary |
|
||
| --- | --- |
|
||
| Saved history | Existing Takes stay readable. Old v5 or unsafe history is not repaired or promoted into reusable Sampling v6 history; start a new Run when required. |
|
||
| Unknown MODEL wrappers | Fresh generation remains available; reuse requires observable, matching contracts. No blanket approval by class name or version. |
|
||
| Attention / Spectrum | Finite audited profiles support Core PyTorch/Kitchen and specified Spectrum implementations, including upstream v0.2.29. [Exact scope](docs/ISSUE31_SAMPLING_SIGNATURES.md). |
|
||
| KJ Model Preview Override | Only the pinned KJ/Core source profile: **VAE / Audio VAE disconnected, Tiny VAE `none`**, Core NoPreviews/Auto/Latent2RGB. KJNodes 1.5.2 alone is insufficient; the audited local source differs from upstream. [Supported hashes](docs/KJ_PREVIEW_OVERRIDE_V398.md). |
|
||
|
||
Published **v3.9.9** passed new-Run, separate-Queue Chunk 1→2 GPU continuation
|
||
with **PyTorch + KJ** and **Comfy Kitchen INT8 + audited local Spectrum + KJ**.
|
||
Preview images remained held, original Chunk 1 data/contracts stayed unchanged,
|
||
and all four video/audio outputs decoded successfully.
|
||
These were 512×512, 24fps, 2×5-second, 8-step Turbo Core-API tests on an RTX 5060 Ti 16 GB.
|
||
They do not establish support for other KJ/Spectrum builds or preview-VAE paths.
|
||
[Full conditions and verification limits](docs/RELEASE_NOTES_V398.md).
|
||
|
||
## Known limitations
|
||
|
||
- **Reference Plan Inspector:** stale display after repeated Sampler configuration
|
||
remains a known issue; the two expected test failures do not mean it is fixed.
|
||
- **Mobile:** reduced UI work is verified; mobile freeze resolution is unconfirmed.
|
||
- **Resources:** nine high-resolution References or long final decoding can exhaust
|
||
VRAM/RAM. Disk-backed Finalize does not prevent allocations in other nodes.
|
||
- **Refinement:** high-ratio latent resize can cause artifacts; longer Hi-Res/Hybrid
|
||
cases and doubled outlines remain limited or under investigation ([Issue #27](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/issues/27)).
|
||
- **Continuity:** exact identity, motion, lip sync and frame-by-frame reproduction
|
||
are not guaranteed. Some long continuations have known quality limits.
|
||
- **Acceptance:** browser Run-button/save-reload, the reporter's exact full graph,
|
||
other provider builds, subjective quality and speed/VRAM benchmarks were not
|
||
established by the targeted v3.9.9 GPU recheck.
|
||
|
||
## Detailed documentation
|
||
|
||
| Topic | Read more |
|
||
| --- | --- |
|
||
| Setup, screenshots and complete controls | [Illustrated user guide](docs/USER_GUIDE.md) |
|
||
| Current Reference Images | [V3.9 Reference guide](docs/V39_REFERENCE_INLINE.md) |
|
||
| Updating from V3.8X2 | [Migration and retained contracts](docs/V38_RELEASE_AND_MIGRATION.md) |
|
||
| History, earlier screenshots and implementation notes | [README history](docs/README_HISTORY.md) / [CHANGELOG](CHANGELOG.md) |
|
||
| Current release and GPU verification | [v3.9.9 notes](docs/RELEASE_NOTES_V398.md) / [package validation](PACKAGE_VALIDATION.txt) |
|
||
| Bug reports | [GitHub Issues](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/issues) — include the workflow, status text and `auto-resume disabled:` reason |
|
||
|
||
Historical Releases and tags remain available. Documentation updates on `main`
|
||
do not replace the published v3.9.9 tag or package assets.
|
||
This condensed README changes documentation only; public nodes, official
|
||
workflow JSON/ZIP files, Sampling v6 and existing Runs/Takes are unchanged.
|
||
|
||
## License
|
||
|
||
[MIT](LICENSE). Third-party components retain their own [licenses and notices](THIRD_PARTY_NOTICES.md).
|