modelscope / modelscope/DiffSynth-Studio
can't load flux text_encoder_2 from local file
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
@mi804
My training machine cannot connect to the Internet, so I need to load the model locally. Flux text_encoder_2 is not in model_loader_configs, which causes the match to fail.
https://github.com/modelscope/DiffSynth-Studio/blob/main/diffsynth/configs/model_config.py#L80
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in diffsynth/configs/model_config.py around line 80 and inspect how model_loader_configs matches Flux components. Add the missing text_encoder_2 configuration so a locally available Flux model can be matched without Internet access, then verify the local-loading path recognizes it.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 52/100