modelscope / modelscope/DiffSynth-Studio
Can we change LoRA scale (lora_alpha) or LoRA without reloading entire pipe? Wan 2.1
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
This is the only example I have found and it is full pipe loading
Can load - deload LoRA can be done without re-loading entire pipe?
Can we change LoRA scale / strength / lora_alpha without reloading entire pipe?
Thank you so much
model_manager.load_lora("models/lightning_logs/version_1/checkpoints/epoch=0-step=500.ckpt", lora_alpha=1.0)
pipe = WanVideoPipeline.from_model_manager(model_manager, device="cuda")
pipe.enable_vram_management(num_persistent_param_in_dit=None)
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 the shown model_manager.load_lora call and WanVideoPipeline.from_model_manager entry point. Determine whether LoRA loading, unloading, and lora_alpha or strength changes can be supported without reloading the full pipeline; done should include a documented, working approach or a clear limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100