Stable Diffusion is an AI art engine created by Stability AI. Popularly used in installations such as Automatic1111 webgui (https://github.com/AUTOMATIC1111/stable-diffusion-webui) and others. This tag covers problems with the engine and installations that bundle other interfaces, as well as prompt crafting and workflows for all functions that Stable Diffusion supports. Training, image to image, etc.
Questions tagged [stable-diffusion]
210 questions
-1
votes
1 answer
stable-diffusion-webui doesnt start
I installed everything, but I get the error ModuleNotFoundError: No module named 'wcwidth', even though I install 'wcwidth' via pip, it still gives the same error
I installed wcwidth I expected it to work but it didn't
patatsci
- 1
- 4
-1
votes
1 answer
Resize any image to 512 x 512
I am trying to train a stable diffusion model, which receives 512 x 512 images as inputs.
I am downloading the bulk of images from the web, and they have multiple sizes and shapes, and so I need to preprocess them and convert to 512 x 512.
If I take…
8-Bit Borges
- 9,643
- 29
- 101
- 198
-1
votes
1 answer
Colab FileNotFoundError - Stable Diffusion Unfiltered
so I'm a complete nawb to this. I googled the problem but found only a bunch of unrelated entries.
I'm trying to run this (stable-diffusion):
https://colab.research.google.com/drive/1uWCe41_BSRip4y4nlcB8ESQgKtr5BfrN#scrollTo=lTRtiZZk0h5d
And…
Oundrey
- 1
- 3
-1
votes
1 answer
How do I introduce a new subject without extra training in Stable Diffusion?
Suppose I have a dataset of 1000 pokemon, I have 10 images of Pikachu, 10 images of Bulbasaur, etc.
I also have a metadata specifying the name of each pokemon exactly. So from the metadata, I can know which image is Pikachu and which image is not.
I…
off99555
- 3,797
- 3
- 37
- 49
-1
votes
1 answer
In Diffusion Models literature, what do they mean by "the reversal of the diffusion process has the identical functional form as the forward process"?
I am trying to understand Diffusion Probabilistic Models, in particular the paper by (Sohl-Dickstein et al. 2015 https://arxiv.org/abs/1503.03585). When defining the backward diffusion model, they take the conditional probability of one step…
yoyod
- 1
-2
votes
0 answers
Stable Diffusion (Couldn't Install )
I have tried several ways:
Checking the Python version
Editing "set COMMANDLINE_ARGS"
These still cannot fix the problems. Any ideas on how to fix the issues?
-2
votes
0 answers
Running AUTOMATIC1111's Stable Diffusion API on Mac
I'm trying to incorporate the stable diffusion service using AUTOMATIC1111's Stable Diffusion Web UI API, whose documentation is written here
As suggested by the documentation, I sent a post request using the…
J Qin
- 13
- 3
-2
votes
0 answers
How to clone voice for songs with different voices?
I've been checking TTS and voice cloning, then I came across this video, which seems to be a song of x being sang by different singers other than x, I was checking differet TTS projects but it doesn't seem to be cabaple of doing so, how/what kind of…
Exorcismus
- 2,243
- 1
- 35
- 68
-2
votes
0 answers
Files stop downloading when installing stable-diffusion-webui
Trying to run stable diffusion web ui on amazon linux but it always pauses when running the files. I am following steps on https://github.com/AUTOMATIC1111/stable-diffusion-webui.
Screenshot of when files stop downloading
pretty sure i have…
benjiboy46
- 1
- 1
-2
votes
1 answer
Automatic1111 API
I'm trying to use the Automatic1111 Stable Diffusion API to make a new StableDiffusion web UI using Svelte.
The API calls just don't seem to work, even when I'm trying it through the official documentation at…
-2
votes
1 answer
Runtime Error or Generating Error | WebUI generate a image showing many fragements
Environment
Mac OS Ventura 13.2.1
Intel Core I9 8 core
AMD Radeon Pro 5500m 4GB
16GB Memory
I want to just show demo with using WebUI. So I need to just WebUI working.
COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae…
Alrock
- 1
- 2
-2
votes
1 answer
'Image' object is not callable
I've been playing around with stable diffusion on Google colab, and I've been having some trouble getting a grid to work. Every time I run my image generator block, it gets through the generation but can't display the images, it gives me the error…
CD912
- 1
- 2
-3
votes
2 answers
(Solved)No mudule named "open_clip.tokenizer" and "xformers" when using stable diffusion
fatal: unable to access 'https://github.com/AUTOMATIC1111/stable-diffusion-webui.git/': Recv failure: Connection was reset
venv "D:\Stable_Diffusion\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022,…
Ernie Nishino
- 1
- 2
-4
votes
0 answers
Stable Diffusion: Get exact Outfit of reference image in generated Image?
(Using Stable Diffusion)
Is there a way to use a reference image in controlnet (or simelar?) and get a output picture with the excact same clothes/outfit?
It can be a completly different composition, just want to keep the outfit.
This would be a…
