[Bug]: create bad image

[LanFly]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

No matter what parameters I use to generate images, they are always terrible.

Steps to reproduce the problem

1. luanch webui.sh using "--skip-torch-cuda-test --upcast-sampling --no-half --no-half-vae --use-cpu interrogate"
2. using prompt "photo of woman, dress, city night background"
3. click generate button

What should have happened?

a normal image

Commit where the problem happens

5ab7f213

What platforms do you use to access the UI ?

MacOS

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--skip-torch-cuda-test --upcast-sampling --no-half --no-half-vae --use-cpu interrogate

List of extensions

NO

Console logs

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on lan user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
Python 3.10.11 (main, Apr  7 2023, 07:33:46) [Clang 14.0.0 (clang-1400.0.29.202)]
Commit hash: 5ab7f213bec2f816f9c5644becb32eb72c8ffb89
Installing requirements
Launching Web UI with arguments: --skip-torch-cuda-test --upcast-sampling --no-half --no-half-vae
/Users/lan/Documents/my-workspace/stable-diffusion-webui/modules/mac_specific.py:52: UserWarning: torch.cumsum supported by MPS on MacOS 13+, please upgrade (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/native/mps/operations/UnaryOps.mm:264.)
  cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from /Users/lan/Documents/my-workspace/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Creating model from config: /Users/lan/Documents/my-workspace/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 9.6s (load weights from disk: 0.5s, create model: 0.8s, apply weights to model: 4.1s, move model to device: 4.0s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 19.9s (import torch: 1.9s, import gradio: 1.9s, import ldm: 0.6s, other imports: 1.7s, setup codeformer: 0.1s, load scripts: 0.9s, load SD checkpoint: 9.6s, opts onchange: 1.6s, create ui: 1.2s, gradio launch: 0.2s).
100%|███████████████████████████████████████████████████████████████| 25/25 [04:43<00:00, 11.35s/it]
Total progress: 100%|███████████████████████████████████████████████| 25/25 [04:35<00:00, 11.01s/it]
Total progress: 100%|███████████████████████████████████████████████| 25/25 [04:35<00:00, 12.71s/it

Additional information

I tried other models and the results were the same

[Iheuzio]

your mac os may require an update, can you attempt that and see if it regulates the issue?

[LanFly]

your mac os may require an update, can you attempt that and see if it regulates the issue?

My MacOS version is 13.3.1 now. The problem still exists.

In addition, I tried torch v1.13 and v2.0.

[emmajane1313]

Was there any fix to this? Getting the same error on Mac1 with the latest a1111 version