modelscope / modelscope/DiffSynth-Studio
Why not loading tokenizers in when loading FLUX.1-dev?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
In the code "/root/DiffSynth-Studio/examples/flux/model_inference/FLUX.1-dev.py"
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
],
)
Why not loading tokenizers in when loading FLUX.1-dev as Qwen-Image does?
It seems that the FLUX in DIffSynth-Studio performs poorer than official repo in diffusers/modelscope
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 with examples/flux/model_inference/FLUX.1-dev.py, especially the FluxImagePipeline.from_pretrained configuration, and compare it with the Qwen-Image loading path referenced in the issue. Investigate whether tokenizer loading relates to the reported FLUX.1-dev quality difference, then document the cause or reproduce the expected behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100