lllyasviel / lllyasviel/stable-diffusion-webui-forge

FAULT in FORGE FLUX Sampling (points or spaces changes the image)

Open
#2,522 3 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

very simple to check

choose the original model FLUX 16 or 8FP

prompt
"portrait photography of a young woman. background suggest a window and a cozy room."
25 step with Forge-Flux and BETA or SGMuniform

and prompt again
"portrait photography of a young woman. background suggest a window and a cozy room. "
importand only some spaces

and -> different image!!!

all other sampler dont change the image only because some spaces or points (yes also with points FLUX-Forge change the image)

what is the explanation ???

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

Reproduce the report with the original FLUX 16 or 8FP model, 25 steps, Forge-Flux, and the BETA or SGMuniform sampler. Compare the exact prompt with and without trailing spaces or punctuation, then trace the sampling path to explain why those prompts produce different images and document the expected behavior.

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
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.