Questions tagged [stable-diffusion]

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.

210 questions
0
votes
0 answers

work around for the operator 'aten::cumprod.out' not being implemented for the MPS device

The operator 'aten::cumprod.out' is not current implemented for the MPS device. How can I manually calculate it?
itsDanial
  • 105
  • 1
  • 10
0
votes
0 answers

HTTP Error on running ControlNet in Google Colab

So, I'm installing stable diffusion with google colab Copy of fast_stable_diffusion_AUTOMATIC1111.ipynb - Colaboratory (google.com) and then running ControlNet (All 21GB), I'm getting this error message: HTTPError Traceback (most recent call last)…
0
votes
0 answers

DreamBooth CUDA out of memory error when no other processes running and GPU usage 0-1%

I'm trying to train a dreambooth model. The first attempt with this data set went fine. I'm now getting the following error. The only thing I have done is increase the steps to 3400, from a previous 2180. it uploads and saves all the files,…
0
votes
1 answer

AttributeError: 'CLIPVisionModelWithProjection' object has no attribute 'get_image_features'

I am working on a stable diffusion model while implementing a simple code example given below in the link. I have followed the same steps mentioned in the link, but still it gives an…
0
votes
1 answer

Stablediffusionweb automation not working in selenium python

I want to automate stablediffusionweb using python selenium but it is giving an error: selenium.common.exceptions.NoSuchElementException: Message: no such element: Unable to locate element: {"method":"css…
0
votes
0 answers

Is it possible : The use of Diffusion model (or GAN if neccesary) for a generation of 3D model by inputting 1D vector? 1D-to-3D diffusion model

To my knowledge so far, I only see Diffusion model being used with image -- taking in 2D noise or image data and outputing 2D image. But what if the problem setting is quite different : For only one given 1D vector, I need to generate several random…
0
votes
0 answers

Sizes of tensors must match except in dimension 1. Expected size 16 but got size 32 for tensor number 1 in the list

I have 6464 orginal image dataset and 3232 low_resoluation image that I want to use for high resoluation model with monai package. My problem is that when I run diffusion model for training I got this error: "Sizes of tensors must match except in…
0
votes
0 answers

Dreambooth how to capture images?

I have collected a set of images and separate text files with caption for each image. The text files have the same name as the image file, but with a different extension (txt). Then I try to train using default instructions for training: export…
Crantisz
  • 227
  • 3
  • 13
0
votes
0 answers

Reasons that affect image generation results in stable diffusion

I use the Diffusers MacOS app that created Hugging Face to generate a image, and I use the diffuser python library to generate image with same parameters, but I got the different result. I kept the following parameters the same in both…
0
votes
0 answers

How to automate inpainting process from stable diffusion?

Hello dear StackOverflow community, I am currently working on a project with stable diffusion. In this project the clothes of a person in a photo should be exchanged with any other clothes. If I do it manually (via stable diffsuion web ui) it works…
0
votes
2 answers

How to install Stable Diffusion web UI from AUTOMATIC1111 on a Mac Intel?

I've recently tried to use the Stable Diffusion web UI from AUTOMATIC1111 on my Mac Intel. There is no documentation for Mac Intel, and when I tried to use the methods presented for other platforms, I ended-up with a Python exception related to…
0
votes
0 answers

Diffusion model text encoding concatenation dimensions

I'm trying to understand how diffusion models, like stable diffusion, work. From what I've understood, there is a split autoencoder at the start and end, and in the middle there is a denoiser network. After encoding, the latent representation of the…
Nyxeria
  • 363
  • 1
  • 4
  • 12
0
votes
0 answers

Error using Stable Diffusion: cannot import name 'is_modelcards_available' from 'diffusers.utils.import_utils'

I'm new to Stable Diffusion; I've followed their instructions to install it https://huggingface.co/blog/stable_diffusion but when I run: from diffusers import StableDiffusionPipeline I get the error ImportError: cannot import name…
datadatadata
  • 119
  • 6
0
votes
1 answer

OSerror when attempting to run Google Colab Deforum Stable Diffusion 0.7

oserrorOSerror when attempting to run Google Colab Deforum Stable Diffusion 0.7. It worked previously, but sudden it is not working. enter image description here i tried many times, different browser, can't worked. Could someone help me with it…
Akash
  • 1
  • 1
0
votes
1 answer

"python --version" not working even after installation and adding path to env variables

When typing "python --version" into cmd, I get the following error: Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases. "py --version" works, but I…