lllyasviel / lllyasviel/stable-diffusion-webui-forge

Flux starts adding horizontal stripes to images around 2K resolution

Open
#1,712 156 comments 10 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

It might be an upstream issue.

I'm using Forge with default settings, except for the resolution. However, I’ve tried most of the samplers and schedulers to fix the problem, but without success. What's particularly frustrating is that the issue randomly disappears once in a while for reasons unknown to me.

Whether I create a 2K image in one step or upscale one from 1K, I often—but not always—get horizontal stripes. I initially suspected it was caused by a LoRA, and while it sometimes seems worse when I use LoRAs, the issue also happens with vanilla Flux. Using FP16 doesn’t help either; in fact, it might even make things worse.

It’s not just my images either. I often see horizontal stripes in Flux-generated images online, although they are usually subtle, as most people don’t post upscaled Flux images in the places I visit.

Occasionally, I manage to create almost stripe-free images at 2K, and sometimes I get no stripes at all with the same image and settings—maybe 1 out of 10 times—but I have no idea why.

I have never had such an issue with any SDXL model.

Please refer to the attached screenshots.

![00017-3769130604](https://github.com/user-attachments/assets/3495987e-dfb9-4617-9566-695a360c7ed7)
![00067-3209157356](https://github.com/user-attachments/assets/ec82f51f-f134-43a0-829d-42cf35455d93)
![00010-3588118394](https://github.com/user-attachments/assets/c6e60bbe-762e-40c2-b9e3-d045cf6d5ab0)

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

Review the 156-comment thread and attached screenshots first, since the issue names no files or tests. Reproduce 2K Flux generation with default settings, comparing direct generation and 1K upscaling across the reported sampler, scheduler, LoRA, and FP16 variations. Done means establishing reliable reproduction conditions and determining whether the stripes originate in Forge or upstream.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.