lllyasviel / lllyasviel/FramePack
[Feature Request] Loading LLM and CLIP in .safetensors format
Open
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, I would really love to see the implementation of loading custom LLM and CLIP from .safetensors models. Maybe through command line arguments like --llm-path and --clip-path.
Thanks in advance!
Contributor guide
No contributing guide indexed for this repository
Research direction
No files or tests are named. Start by locating the existing LLM and CLIP loading paths and command-line argument definitions, then determine how custom .safetensors models should be selected through --llm-path and --clip-path. Done means both model types can be loaded in that format through the requested arguments.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100