Update README.md
This commit is contained in:
@@ -1,10 +1,13 @@
|
|||||||
# ComfyUI-H3-Continuum 3.8.1 — V3.8X
|
# ComfyUI-H3-Continuum 3.8.1 — V3.8X
|
||||||
|
|
||||||
> This is the current **V3.8X / package 3.8.1 guide**. It documents the supported seven-node surface and the supplied V3.8X workflow. The older V3.8.0 package remains available from tag [`v3.8.0`](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/tree/v3.8.0); do not combine its workflow or instructions with this guide.
|
|
||||||
|
|
||||||
**Download V3.8X workflow: [JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) | [ZIP](examples/workflows/MiniMax_H3_Continuum_V38x.zip)** — [Latest release](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/releases/latest)
|
![Uploading exec-7cbb1899-cece-4794-b94f-c287dc62b2a9.png…]()
|
||||||
|
|
||||||
✅ V3.8X on `main` includes the September 8, 2026 Review hotfix: Review Each Chunk continuation, stale `Regenerate From` state, completed-sequence extension, and Render History queue handling are repaired. Update with `git pull --ff-only origin main` (or ComfyUI Manager **Update**), restart ComfyUI, and hard-refresh the browser if the old UI remains. Existing saved Takes are preserved. Issue #13 remains a separate open long-continuation quality issue and is not part of this hotfix.
|
|
||||||
|
> This is the current **V3.8X / package 3.8.1 guide**. It documents the supported seven-node surface and the supplied V3.8X workflow. The older V3.8.0 package remains available from tag [`v3.8.0`](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/tree/v3.8.0); do not combine its workflow or instructions with this guide.
|
||||||
|
|
||||||
|
**Download V3.8X workflow: [JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) | [ZIP](examples/workflows/MiniMax_H3_Continuum_V38x.zip)** — [Latest release](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/releases/latest)
|
||||||
|
|
||||||
|
✅ V3.8X on `main` includes the September 8, 2026 Review hotfix: Review Each Chunk continuation, stale `Regenerate From` state, completed-sequence extension, and Render History queue handling are repaired. Update with `git pull --ff-only origin main` (or ComfyUI Manager **Update**), restart ComfyUI, and hard-refresh the browser if the old UI remains. Existing saved Takes are preserved. Issue #13 remains a separate open long-continuation quality issue and is not part of this hotfix.
|
||||||
|
|
||||||
|
|
||||||
H3 Continuum is a Production Sampler for generating, reviewing, partially regenerating, and resuming long-form MiniMax H3 video without restarting the entire work. V3.8 has two product layers: **Main / Production** and **Advanced**.
|
H3 Continuum is a Production Sampler for generating, reviewing, partially regenerating, and resuming long-form MiniMax H3 video without restarting the entire work. V3.8 has two product layers: **Main / Production** and **Advanced**.
|
||||||
@@ -25,18 +28,18 @@ cd ComfyUI/custom_nodes/ComfyUI-H3-Continuum
|
|||||||
git pull --ff-only origin main
|
git pull --ff-only origin main
|
||||||
```
|
```
|
||||||
|
|
||||||
Restart ComfyUI after cloning or pulling. If ComfyUI Manager installed the node, use its **Update** action instead of mixing Manager updates with a second Git checkout.
|
Restart ComfyUI after cloning or pulling. If ComfyUI Manager installed the node, use its **Update** action instead of mixing Manager updates with a second Git checkout.
|
||||||
|
|
||||||
To install the historical V3.8.0 package into a separate checkout instead:
|
To install the historical V3.8.0 package into a separate checkout instead:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
cd ComfyUI/custom_nodes
|
cd ComfyUI/custom_nodes
|
||||||
git clone --branch v3.8.0 --single-branch https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum.git ComfyUI-H3-Continuum-v3.8.0
|
git clone --branch v3.8.0 --single-branch https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum.git ComfyUI-H3-Continuum-v3.8.0
|
||||||
```
|
```
|
||||||
|
|
||||||
Use only one Continuum checkout at a time. ComfyUI Manager **Update** tracks `main`; it does not select historical tags.
|
Use only one Continuum checkout at a time. ComfyUI Manager **Update** tracks `main`; it does not select historical tags.
|
||||||
|
|
||||||
Download the current V3.8X workflow: [JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) or [ZIP containing the same JSON](examples/workflows/MiniMax_H3_Continuum_V38x.zip). This is one Spectrum-capable graph, also usable with [LightX2V Turbo](https://github.com/ModelTC/Minimax-H3-Turbo); both Spectrum and all Turbo LoRA entries are saved disabled. Install its external Spectrum, rgthree, and KJNodes nodes before opening it. ComfyUI-Easy-Use is not required. See [Spectrum and Turbo setup](#turbo-lora-and-spectrum-in-supplied-workflows) below.
|
Download the current V3.8X workflow: [JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) or [ZIP containing the same JSON](examples/workflows/MiniMax_H3_Continuum_V38x.zip). This is one Spectrum-capable graph, also usable with [LightX2V Turbo](https://github.com/ModelTC/Minimax-H3-Turbo); both Spectrum and all Turbo LoRA entries are saved disabled. Install its external Spectrum, rgthree, and KJNodes nodes before opening it. ComfyUI-Easy-Use is not required. See [Spectrum and Turbo setup](#turbo-lora-and-spectrum-in-supplied-workflows) below.
|
||||||
|
|
||||||
## Prompt and skill downloads
|
## Prompt and skill downloads
|
||||||
|
|
||||||
@@ -48,7 +51,7 @@ These are optional prompt-authoring resources, not ComfyUI custom nodes. Extract
|
|||||||
|
|
||||||
## You can ask an AI to read this manual
|
## You can ask an AI to read this manual
|
||||||
|
|
||||||
This README is intentionally detailed. You do not have to memorize it. Give its GitHub URL or this file to a web-enabled AI, describe your target video, GPU/VRAM, available First Image/audio, and whether you want to review every chunk. Ask it to use the **exact V3.8 labels** below.
|
This README is intentionally detailed. You do not have to memorize it. Give its GitHub URL or this file to a web-enabled AI, describe your target video, GPU/VRAM, available First Image/audio, and whether you want to review every chunk. Ask it to use the **exact V3.8 labels** below.
|
||||||
|
|
||||||
Example request:
|
Example request:
|
||||||
|
|
||||||
@@ -59,7 +62,7 @@ Continuum inputs and controls to use, what must stay fixed between Queue runs,
|
|||||||
and what output length I should expect after each action. Do not use older V3.7 UI.
|
and what output length I should expect after each action. Do not use older V3.7 UI.
|
||||||
```
|
```
|
||||||
|
|
||||||
AI products, plans, and repository-reading behavior change frequently. If a URL is not read correctly, paste or upload this README instead. Do not send private workflows, local paths, tokens, or credentials to a public AI service. The README and the UI remain the source of truth; an AI summary can still be wrong.
|
AI products, plans, and repository-reading behavior change frequently. If a URL is not read correctly, paste or upload this README instead. Do not send private workflows, local paths, tokens, or credentials to a public AI service. The README and the UI remain the source of truth; an AI summary can still be wrong.
|
||||||
|
|
||||||
## V3.8 supported surface
|
## V3.8 supported surface
|
||||||
|
|
||||||
@@ -281,7 +284,7 @@ The four MiniMax H3 Turbo files shown in the example come from the LightX2V Mini
|
|||||||
|
|
||||||
The number in a Turbo filename is its distilled NFE target. Use the matching upstream recommendation unless a provided workflow explicitly documents a tested exception. In particular, using a 4-step LoRA with `Steps = 6` is a workflow-specific experiment, not the LightX2V default. `Euler`/`simple`, the actual Steps value, and the selected LoRA must be recorded together when comparing results.
|
The number in a Turbo filename is its distilled NFE target. Use the matching upstream recommendation unless a provided workflow explicitly documents a tested exception. In particular, using a 4-step LoRA with `Steps = 6` is a workflow-specific experiment, not the LightX2V default. `Euler`/`simple`, the actual Steps value, and the selected LoRA must be recorded together when comparing results.
|
||||||
|
|
||||||
`Power Lora Loader (rgthree)`, KJNodes SageAttention, and Spectrum are external components. Continuum does not install, enable, or tune them. The [V3.8X workflow](examples/workflows/MiniMax_H3_Continuum_V38x.json) is the single supplied graph, distributed unchanged as JSON and ZIP. Its saved default has Spectrum disabled, no Turbo LoRA enabled, `res_multistep`, `simple`, and `Steps = 20`. These three custom-node packages are required to open the complete graph, including when switching it to Turbo. ComfyUI-Easy-Use is not required.
|
`Power Lora Loader (rgthree)`, KJNodes SageAttention, and Spectrum are external components. Continuum does not install, enable, or tune them. The [V3.8X workflow](examples/workflows/MiniMax_H3_Continuum_V38x.json) is the single supplied graph, distributed unchanged as JSON and ZIP. Its saved default has Spectrum disabled, no Turbo LoRA enabled, `res_multistep`, `simple`, and `Steps = 20`. These three custom-node packages are required to open the complete graph, including when switching it to Turbo. ComfyUI-Easy-Use is not required.
|
||||||
|
|
||||||
The supplied prompt, media selections, and node titles have deliberately been preserved. Choose files available on your computer, disable unused optional inputs, and enter your own prompt before generating. Models, LoRAs, images, and audio are not included. A custom title such as `Save 3x5s Video` is only a saved label: actual duration follows the Sampler's `Chunks` and `Seconds per Chunk`, not that title.
|
The supplied prompt, media selections, and node titles have deliberately been preserved. Choose files available on your computer, disable unused optional inputs, and enter your own prompt before generating. Models, LoRAs, images, and audio are not included. A custom title such as `Save 3x5s Video` is only a saved label: actual duration follows the Sampler's `Chunks` and `Seconds per Chunk`, not that title.
|
||||||
|
|
||||||
@@ -323,7 +326,7 @@ Choose the task you need:
|
|||||||
|
|
||||||
`Chunks` is the **total number of chunks you want**, not the number to add on the next Queue. `Seconds per Chunk` is the duration of each chunk. `Total Length` is the planned final duration; it is not a progress counter.
|
`Chunks` is the **total number of chunks you want**, not the number to add on the next Queue. `Seconds per Chunk` is the duration of each chunk. `Total Length` is the planned final duration; it is not a progress counter.
|
||||||
|
|
||||||
For example, `Chunks = 6` and `Seconds per Chunk = 5` means a 30-second target. With `Run = Review Each Chunk`, the first Queue normally creates only Chunk 1: a 5-second video. Continuing generates the next review unit. During review, the preview/save output is the **current review unit** (normally 5 seconds), not an accumulating preview. After the run reaches `complete`, or after `Use it and finish the rest` generates the remaining chunks, Finalize outputs the assembled completed sequence.
|
For example, `Chunks = 6` and `Seconds per Chunk = 5` means a 30-second target. With `Run = Review Each Chunk`, the first Queue normally creates only Chunk 1: a 5-second video. Continuing generates the next review unit. During review, the preview/save output is the **current review unit** (normally 5 seconds), not an accumulating preview. After the run reaches `complete`, or after `Use it and finish the rest` generates the remaining chunks, Finalize outputs the assembled completed sequence.
|
||||||
|
|
||||||
The screenshots show **two chunks as a small example**. The same controls apply to three, four, five, six, or another supported total.
|
The screenshots show **two chunks as a small example**. The same controls apply to three, four, five, six, or another supported total.
|
||||||
|
|
||||||
@@ -552,9 +555,9 @@ Driving Audio can be used with Review and Smart Regenerate. The Continuum Image,
|
|||||||
|
|
||||||
> **Second Pass limitation:** Finish the reviewed sequence before running Second Pass. Second Pass / `refine_context` is not supported on a partial Review sequence.
|
> **Second Pass limitation:** Finish the reviewed sequence before running Second Pass. Second Pass / `refine_context` is not supported on a partial Review sequence.
|
||||||
|
|
||||||
## Archived implementation notes (pre-V3.8; not the current guide)
|
## Archived implementation notes (pre-V3.8; not the current guide)
|
||||||
|
|
||||||
The version-labelled sections below are retained temporarily as source history only. They do not describe the V3.8 standard workflow, public surface, or recommended wiring. For an older workflow, use the migration policy and its matching historical Release/tag.
|
The version-labelled sections below are retained temporarily as source history only. They do not describe the V3.8 standard workflow, public surface, or recommended wiring. For an older workflow, use the migration policy and its matching historical Release/tag.
|
||||||
|
|
||||||
### V3.7 High-Resolution Refinement Foundation
|
### V3.7 High-Resolution Refinement Foundation
|
||||||
|
|
||||||
@@ -650,7 +653,7 @@ Prompt/CLIP figures measure only the conditioning subphase, not total generation
|
|||||||
|
|
||||||
The measured Sage-only production baselines on the tested RTX 5060 Ti 16 GB / 64 GB system were 168.069 seconds for 1×5-second 576×576 T2VA and 379.765 seconds for 3×5-second 640×640 FL2VA Long Terminal Merge. These are configuration-specific baselines, not universal speed guarantees. Sampling remained the dominant cost; Continuum Assemble + Seam stayed below 1%.
|
The measured Sage-only production baselines on the tested RTX 5060 Ti 16 GB / 64 GB system were 168.069 seconds for 1×5-second 576×576 T2VA and 379.765 seconds for 3×5-second 640×640 FL2VA Long Terminal Merge. These are configuration-specific baselines, not universal speed guarantees. Sampling remained the dominant cost; Continuum Assemble + Seam stayed below 1%.
|
||||||
|
|
||||||
> **V3.8.0 is the historical release baseline.** The current release candidate is V3.8X / package 3.8.1. Historical implementation modules remain in source because V3.8X reuses them internally. Only the seven current public nodes are exported, including the earlier IDs retained for those nodes. Use the matching historical Release/tag for workflows requiring other IDs. Still Image Guide remains Experimental.
|
> **V3.8.0 is the historical release baseline.** The current release candidate is V3.8X / package 3.8.1. Historical implementation modules remain in source because V3.8X reuses them internally. Only the seven current public nodes are exported, including the earlier IDs retained for those nodes. Use the matching historical Release/tag for workflows requiring other IDs. Still Image Guide remains Experimental.
|
||||||
|
|
||||||
## V3.5.1 Reference Audio & Compatibility Update
|
## V3.5.1 Reference Audio & Compatibility Update
|
||||||
|
|
||||||
@@ -699,7 +702,7 @@ The external workflow owns AV LATENT pairing, noise, SIGMAS, Audio Lock, samplin
|
|||||||
|
|
||||||

|

|
||||||
|
|
||||||
The retired V3.5.1 LBH + Conditioning Bridge example is available only from its matching historical Release/tag; it is not a V3.8 workflow.
|
The retired V3.5.1 LBH + Conditioning Bridge example is available only from its matching historical Release/tag; it is not a V3.8 workflow.
|
||||||
|
|
||||||
The example keeps the standard Core titles `BasicGuider`, `BasicScheduler`, and `SamplerCustomAdvanced`. Public examples do not rename Core nodes, so they remain immediately distinguishable from Continuum and third-party nodes. The workflow also uses external nodes for LBH latent upscaling, AV LATENT concatenation/separation, loading/saving, and optional acceleration; install or replace those nodes according to your ComfyUI environment.
|
The example keeps the standard Core titles `BasicGuider`, `BasicScheduler`, and `SamplerCustomAdvanced`. Public examples do not rename Core nodes, so they remain immediately distinguishable from Continuum and third-party nodes. The workflow also uses external nodes for LBH latent upscaling, AV LATENT concatenation/separation, loading/saving, and optional acceleration; install or replace those nodes according to your ComfyUI environment.
|
||||||
|
|
||||||
@@ -833,10 +836,10 @@ This is a usability and reliability decision, not a claim that the experimental
|
|||||||
|
|
||||||
## Example workflow
|
## Example workflow
|
||||||
|
|
||||||
- [V3.8X workflow JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) — Spectrum disabled by default; switch the same graph to LightX2V Turbo as described above
|
- [V3.8X workflow JSON](examples/workflows/MiniMax_H3_Continuum_V38x.json) — Spectrum disabled by default; switch the same graph to LightX2V Turbo as described above
|
||||||
- [V3.8X workflow ZIP](examples/workflows/MiniMax_H3_Continuum_V38x.zip) — contains exactly the same JSON, not another variant or a custom-node installer
|
- [V3.8X workflow ZIP](examples/workflows/MiniMax_H3_Continuum_V38x.zip) — contains exactly the same JSON, not another variant or a custom-node installer
|
||||||
|
|
||||||
The declared Registry payload includes this one graph in both formats; it is **not dependency-free**. Spectrum, rgthree, and KJNodes must be installed separately; ComfyUI-Easy-Use is not required. Historical workflow files remain in GitHub source but are excluded from the Registry payload. For an older saved workflow, use its matching historical Release/tag as described in the [migration policy](docs/V38_RELEASE_AND_MIGRATION.md). Registry packaging validation/publication is separate from this GitHub source update.
|
The declared Registry payload includes this one graph in both formats; it is **not dependency-free**. Spectrum, rgthree, and KJNodes must be installed separately; ComfyUI-Easy-Use is not required. Historical workflow files remain in GitHub source but are excluded from the Registry payload. For an older saved workflow, use its matching historical Release/tag as described in the [migration policy](docs/V38_RELEASE_AND_MIGRATION.md). Registry packaging validation/publication is separate from this GitHub source update.
|
||||||
|
|
||||||
## V3.4 feature details
|
## V3.4 feature details
|
||||||
|
|
||||||
@@ -942,7 +945,7 @@ git pull --ff-only origin main
|
|||||||
|
|
||||||
Restart ComfyUI after the update. If the node was installed with ComfyUI Manager, use its **Update** action instead of running `git pull` manually. Do not mix Manager updates and a separate Git checkout for the same installation.
|
Restart ComfyUI after the update. If the node was installed with ComfyUI Manager, use its **Update** action instead of running `git pull` manually. Do not mix Manager updates and a separate Git checkout for the same installation.
|
||||||
|
|
||||||
After the backend restart, search for `H3 Continuum Sampler V3.8`. The complete V3.8X search surface contains the seven nodes listed above. If they are missing, check the startup console for the `H3 Continuum 3.8.1 loaded` message and any `ComfyUI-H3-Continuum` import error.
|
After the backend restart, search for `H3 Continuum Sampler V3.8`. The complete V3.8X search surface contains the seven nodes listed above. If they are missing, check the startup console for the `H3 Continuum 3.8.1 loaded` message and any `ComfyUI-H3-Continuum` import error.
|
||||||
|
|
||||||
Search for H3 Continuum or Continuum in ComfyUI Manager, or install manually:
|
Search for H3 Continuum or Continuum in ComfyUI Manager, or install manually:
|
||||||
|
|
||||||
@@ -1250,13 +1253,13 @@ Both inputs are optional. Connect `Video Guide Frames` when video guidance is ne
|
|||||||
|
|
||||||
Use a 24 fps source for `Video Guide Frames`. `Load Video (Upload)` may accept files recorded at 25 fps or another frame rate, but acceptance alone does not guarantee correct temporal alignment with H3. For a non-24 fps source, set `force_rate` to `24` in `Load Video (Upload)`, or convert the file to 24 fps before loading it. If the source is already 24 fps, leave `force_rate` at its default and do not resample it.
|
Use a 24 fps source for `Video Guide Frames`. `Load Video (Upload)` may accept files recorded at 25 fps or another frame rate, but acceptance alone does not guarantee correct temporal alignment with H3. For a non-24 fps source, set `force_rate` to `24` in `Load Video (Upload)`, or convert the file to 24 fps before loading it. If the source is already 24 fps, leave `force_rate` at its default and do not resample it.
|
||||||
|
|
||||||
## Current validation status
|
## Current validation status
|
||||||
|
|
||||||
The V3.8 public-surface suite checks the exact seven-node export, the supplied Spectrum graph and matching ZIP payload, declared external dependencies, Registry exclusions, preserved V3.8 widget/socket order, and presentation-only `Show Advanced Settings` / `Hide Advanced Settings` behavior. Registry payload hashes are recorded in `REGISTRY_MANIFEST.sha256`; source integrity is recorded in `MANIFEST.sha256`.
|
The V3.8 public-surface suite checks the exact seven-node export, the supplied Spectrum graph and matching ZIP payload, declared external dependencies, Registry exclusions, preserved V3.8 widget/socket order, and presentation-only `Show Advanced Settings` / `Hide Advanced Settings` behavior. Registry payload hashes are recorded in `REGISTRY_MANIFEST.sha256`; source integrity is recorded in `MANIFEST.sha256`.
|
||||||
|
|
||||||
**Latest local RC evidence:** the full CPU suite passed **1,261 passed / 1 skipped / 0 failed**. The final dedicated GPU Functional Gate passed a `3 × 5 second` Review Each Chunk run: Q1–Q3 generated one physical group at a time, and Q4 reused all three groups with `3 reused / 0 generated`. Q3 and Q4 had identical decoded RGB and PCM SHA-256 values. This confirms functional execution, prefix reuse, and AV reconstruction; it is not a full subjective image- or audio-quality rating.
|
**Latest local RC evidence:** the full CPU suite passed **1,261 passed / 1 skipped / 0 failed**. The final dedicated GPU Functional Gate passed a `3 × 5 second` Review Each Chunk run: Q1–Q3 generated one physical group at a time, and Q4 reused all three groups with `3 reused / 0 generated`. Q3 and Q4 had identical decoded RGB and PCM SHA-256 values. This confirms functional execution, prefix reuse, and AV reconstruction; it is not a full subjective image- or audio-quality rating.
|
||||||
|
|
||||||
Validation results apply to the tested local source and environment. They do not guarantee that an installed copy is current, that all models/wrappers fit every GPU, or that a different prompt will have the same visual quality.
|
Validation results apply to the tested local source and environment. They do not guarantee that an installed copy is current, that all models/wrappers fit every GPU, or that a different prompt will have the same visual quality.
|
||||||
|
|
||||||
## Limits
|
## Limits
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user