lllyasviel / lllyasviel/stable-diffusion-webui-forge

Flux generates terrible images

Open
#2,542 9 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

I have tried different setups and models but all end up with terrible images.
Here my setups below. Any help? Thanks

I tried to use:
-flux1-dev-bnb-nf4-v2.safetensors

  • flux_dev.safetensors
  • t5xxl_fp16.safetensors
  • t5xxl_fp8_e4m3fn.safetensors
  • ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors
    I tried with lora and wtihout lora too.

image

Here is my system details;
image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the reported image-generation result using the listed Flux, text-encoder, and LoRA setups, together with the supplied system details. Done means identifying a reproducible configuration problem or confirming that the report lacks enough information to isolate one.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.