nodes/olivv-cs-ComfyUI-FunPack
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Document dev branch WIP policy

Browse Source
This commit is contained in:
digital-garbage
2026-04-23 19:37:47 +03:00
parent ac82403cf3
commit eb066ede0b
2 changed files with 7 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -7
View File
@@ -23,6 +23,12 @@ Use this order:
`FunPack Gemma Embedding Refiner` does the prompt/concept/rating work and saves next-run LoRA weight suggestions into its existing refinement JSON. It can improve the balance and stability of concepts the model can already express, but it cannot teach a model missing concepts or capabilities from scratch.
## WIP on `dev`
The `dev` branch contains unstable work-in-progress changes, including the Video Refiner rename, latent refinement experiments, and related LTX video-latent helpers.
Switch to `dev` only if you intentionally want to test unfinished features. For stable daily use, stay on `main`.
## Installation
FunPack is available on Comfy Registry and can be installed in any of these ways:
@@ -30,7 +36,7 @@ FunPack is available on Comfy Registry and can be installed in any of these ways
1. With `comfy-cli`:
`comfy node install ComfyUI-FunPack`
2. With git, inside your `ComfyUI/custom_nodes` directory:
`git clone https://github.com/aimfordeb/ComfyUI-FunPack`
`git clone https://github.com/digital-garbage/ComfyUI-FunPack`
3. With ComfyUI-Manager:
Open `Custom Nodes Manager`, search for `ComfyUI-FunPack`, and click `Install`.
@@ -53,12 +59,6 @@ The expected baseline is:
Higher Torch versions are fine. The important part is avoiding older Torch releases that may break FunPack workflows. If your ComfyUI environment has an older Torch build, upgrade Torch in that environment separately instead of through `requirements.txt`.
## Known Limitation
`FunPack Gemma Embedding Refiner` can optionally refine `SIGMAS`, but that currently breaks audio generation in workflows that also produce audio streams. If you need audio to generate and mux correctly, do not connect `sigmas` to the refiner. Leave sigma schedules on their original path and use the refiner only for conditioning.
UPD: This is not caused by Embedding Refiner node. Updating to latest nightly version of ComfyUI solves the problem.
`hpsv3` is still an optional dependency used only by the `FunPack StoryMem Keyframe Extractor` quality filter, so it is not included in the default requirements.
Install it manually only if you need that feature:
docs/FunPackGemmaEmbeddingRefiner.md
-4
View File
@@ -53,7 +53,3 @@ Use this node when you want to iteratively tune prompt conditioning based on you
This node cannot make the underlying model generate concepts it does not already know how to represent. If a required subject, action, style, object, anatomy detail, or relationship is missing from the model's learned capabilities, repeating ratings will not teach it from scratch.
The refiner can only adjust the strength, balance, stability, and emphasis of concepts that are already present in the model's output space. Use model choice, LoRAs, ControlNet/reference tools, better source images, or prompt changes when a concept is absent rather than merely under-weighted.
## Warning
Sigma refinement currently breaks audio generation in workflows that also produce audio streams. If you need audio to generate and save correctly, do not connect `sigmas` to this node. Use the refiner only for conditioning in those workflows.