lllyasviel / lllyasviel/FramePack

I want to try but so far I haven't had any success.

Open
#543 0 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

almost 2 weeks im trying to run and generate something but still have no luck. I think that my laptop is good - Its a Dell Precission 7740, 2 SSD x 1TB, 128GB RAM, and Quadro RTX 5000 - 16GB VRAM, WIN10 Proffesional, but still cant make it to generate something. Still cant istall working with my GPU Flash or Sage Attention or some of the others accelerators /triton, xformers../ I always get incompatibility errors, bcose of my TURING arhitecture GPU. Without them i got generation speed about 1500-3000s/it and took about 24 hours for 3-4 seconds. So i wanna try NV20 fork, but Im not so fammiliar with these codes and the author not posted "one click installer" and i dont know how to install on my windows. Also i found Flash Attention for Turing GPU /https://github.com/ssiu/flash-attention-turing/ but after install when i check with "list" command i see there as installed, but when i run with "run.bat" its shows "not installed" Can someone guide me step by step - HOW and WHAT to install to got success! Thanks in advance!

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the reported Windows setup using the repository's list command and run.bat, then compare their installed-state results. The issue mentions NV20, Flash Attention for Turing, Triton, and xformers, but does not identify a repository file or failing test; done would require a confirmed compatible installation path or a clearly isolated incompatibility.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, operating-systems
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.