lllyasviel / lllyasviel/stable-diffusion-webui-forge
Deleted functionality like reuse_model_from_already_loaded, load_model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
For my purpose - I need support for fast checkpoing changing via API. But this functionality is basicly deleted:
Here is original implementation from a1111.
Currently it's just unload all models(code is here), without keeping them in RAM or VRAM, or somewhere for fast checkpoint changing. I think we can add new argument, like --enable_checkpointing_in_vram and guys who needs this functionality can just activate that
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
Compare the original implementation in modules/sd_models.py with the current code at the referenced location. Start by tracing reuse_model_from_already_loaded and load_model, then determine how an optional checkpointing setting would preserve models for fast API changes. Done means checkpoint changes can reuse models in RAM or VRAM when the setting is enabled.
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
- Mostly clear
- Newbie friendliness
- 35/100