stable-diffusion-webui
stable-diffusion-webui copied to clipboard
AUTOMATIC1111
[Bug]: SwinIR upscaler producing black bars
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What happened?
specs: AMD RX 6600 XT
Steps to reproduce the problem
Extras -> Upscaler 1 -> SwinIR 4x
What should have happened?
full image
Commit where the problem happens
https://github.com/lshqqytiger/stable-diffusion-webui-directml
What platforms do you use to access the UI ?
No response
What browsers do you use to access the UI ?
No response
Command Line Arguments
--no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1 --medvram --autolaunch
List of extensions
| ultimate-upscale-for-automatic1111 | https://github.com/Coyote-A/ultimate-upscale-for-automatic1111.git | 0a3d03a4 (Tue Feb 7 06:07:23 2023) | unknown |
|---|---|---|---|
| LDSR | built-in | ||
| Lora | built-in | ||
| ScuNET | built-in | ||
| SwinIR | built-in | ||
| prompt-bracket-checker |
Console logs
venv "D:\AI_ART\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb 7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing requirements for Web UI
Launching Web UI with arguments: --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1 --medvram --autolaunch
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [e03274b1e7] from D:\AI_ART\stable-diffusion-webui-directml\models\Stable-diffusion\meinamix_meinaV7.safetensors
Creating model from config: D:\AI_ART\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 5.0s (load weights from disk: 0.1s, create model: 0.5s, apply weights to model: 4.3s).
Running on local URL: http://127.0.0.1:7860
Additional information
No response
I don't know what the cause or full solution is, I'm getting this as well, but you can reduce the effect by going into settings and reducing the tile size on Swin. I dropped it down to 32, and it's just a sliver of a bar. Easily cropped out.
I have the same issue, 2 black tiles in the exact same position as you have mentioned. I couldn't find any solution for this issue. Any help would be greatly appreciated.
fixed for me on Mac MBA M1 by decreasing tile size settings > upscaling > SwinIR tile size to 128 ish
