lllyasviel / lllyasviel/FramePack

[Feature Request] Loading LLM and CLIP in .safetensors format

Open
#33 2 comments 0 reactions 0 assignees View on GitHub
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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.