Comfy-Org / Comfy-Org/ComfyUI

HunyuanImage - Refiner requested

Open
#9,804 9 comments 6 reactions 0 assignees View on GitHub
Feature
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 6h
Merged PRs (30d)
155

Description

### Feature Idea

Thank you very much for implementing HunyuanImage that fast. It comes originally with a refiner. I would love to see it implemented as well. (The refiner VAE doesn't load and the model gets only 4 dimensions but needs 5.)
What about the prompt enhancer? It's not a must have since there is already a custom node for that but if you are working on it, that would be awesome too. But the refiner first since the images really need it. (Faces, Eyes, Hair, Texture... they really need a refinement.)
Thanks!

### Existing Solutions

_No response_

### Other

_No response_

Contributor guide

Open the contributing guide

Research direction

The issue names no files, tests, or entry points. Start by locating the existing HunyuanImage implementation and its VAE/model-loading path; done means the refiner loads with the required five dimensions, while prompt enhancement remains optional.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.