AUTOMATIC1111 / stable-diffusion-webui

Stable Diffusion web UI
GNU Affero General Public License v3.0
140.83k stars 26.64k forks source link

[Bug]: Batch size in img2img does not work properly with Poor man's outpainting #10789

Open hakemz91 opened 1 year ago

hakemz91 commented 1 year ago

Is there an existing issue for this?

What happened?

When you attempt to increase the batch size beyond 1 while performing outpainting using Poor man's outpainting, only one image result will be shown and saved to disk regardless of how much numbers you put. I read about the same issue happened to outpainting mk2 and solved already so hope it can be solved too for this Poor man's outpainting, since it is doing better generation for me than mk2.

Steps to reproduce the problem

  1. Go to the img2img tab
  2. Upload an image
  3. Increase the batch size to 2 or more
  4. Under scripts, Poor man's outpainting
  5. Generate

What should have happened?

The amount of generation images should be according to the set up batch size, and not only outputting one image all the time.

Commit where the problem happens

https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/20ae71faa8ef035c31aa3a410b707d792c8203a3

What Python version are you running on ?

Python 3.10.x

What platforms do you use to access the UI ?

Windows

What device are you running WebUI on?

Nvidia GPUs (RTX 20 above)

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

@echo off

set PYTHON="C:\Users\opd\AppData\Local\Programs\Python\Python310\python.exe"
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--xformers
git pull
call webui.bat

List of extensions

https://github.com/DominikDoom/a1111-sd-webui-tagcomplete.git https://github.com/pharmapsychotic/clip-interrogator-ext.git https://github.com/adieyal/sd-dynamic-prompts.git https://github.com/kohya-ss/sd-webui-additional-networks.git https://github.com/thomasasfk/sd-webui-aspect-ratio-helper.git https://github.com/Mikubill/sd-webui-controlnet.git https://github.com/yankooliveira/sd-webui-photopea-embed https://github.com/AUTOMATIC1111/stable-diffusion-webui-promptgen.git https://github.com/innightwolfsleep/stable-diffusion-webui-randomize.git https://github.com/AUTOMATIC1111/stable-diffusion-webui-rembg.git

Console logs

Already up to date.
venv "C:\FromOSBefore\AITools\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.3.0
Commit hash: 20ae71faa8ef035c31aa3a410b707d792c8203a3
Installing requirements

Launching Web UI with arguments: --xformers
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
ControlNet v1.1.201
ControlNet v1.1.201
Loading weights [0cbf567c8c] from C:\FromOSBefore\AITools\stable-diffusion-webui\models\Stable-diffusion\aZovyaPhotoreal_v1.safetensors
Create LRU cache (max_size=16) for preprocessor results.
Create LRU cache (max_size=16) for preprocessor results.
Creating model from config: C:\FromOSBefore\AITools\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Create LRU cache (max_size=16) for preprocessor results.
Startup time: 5.2s (import torch: 1.1s, import gradio: 0.8s, import ldm: 0.4s, other imports: 0.6s, load scripts: 1.5s, create ui: 0.5s, gradio launch: 0.2s).
DiffusionWrapper has 859.52 M params.
Applying optimization: xformers... done.
Textual inversion embeddings loaded(0):
Model loaded in 3.3s (load weights from disk: 0.6s, create model: 0.6s, apply weights to model: 0.4s, apply half(): 0.5s, move model to device: 0.4s, load textual inversion embeddings: 0.8s).
Poor man's outpainting will process a total of 2 images tiled as 2x2.
100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:04<00:00,  3.98it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:03<00:00,  4.41it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 32/32 [00:07<00:00,  4.12it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:09<00:00,  1.63it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 16/16 [00:09<00:00,  1.61it/s]
Poor man's outpainting will process a total of 2 images tiled as 2x2.██████████████████| 16/16 [00:09<00:00,  1.63it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:03<00:00,  4.43it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:03<00:00,  4.41it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 32/32 [00:07<00:00,  4.14it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 32/32 [00:07<00:00,  4.39it/s]

Additional information

No response

mike-rowley commented 1 year ago

Same issue here