Stack Overflow
Stack Overflow

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
2
votes
1 answer

Unable to move the Stable Diffusion pipeline to my M1 MacBook

I am following the steps stated here: How to use Stable Diffusion in Apple Silicon (M1/M2). At my local MacBook M1 machine, I saved the below script in stable-diffusion.py file: # make sure you're logged in with `huggingface-cli login` from…
Devarshi
  • 16,440
  • 13
  • 72
  • 125
2
votes
1 answer

Error: Couldn't install gfpgan while installing Stable Diffusion Web UI on Mac M1

I'm trying to install Stable Diffusion (1.4) Web UI on Mac M1 but, encountered some errors such as; RuntimeError: Couldn't install gfpgan. ERROR: Unknown compiler(s): RuntimeError: Couldn't install gfpgan. ['gfortran'], ['flang'], ['nvfortran'],…
yuki shima
  • 21
  • 1
  • 2
2
votes
1 answer

How to define prompt weights to huggingface's diffusers.StableDiffusionInpaintPipeline?

I am tweaking a python script using diffusers inpainting pipeline for a custom video generation idea. I would like to gradually shift the weights of certain words in the prompt. As I understand the argument prompt_embeds is exactly what i need. I…
Bálint Komjáti
  • 33
  • 4
2
votes
0 answers

RuntimeError: expected scalar type Float but found Half in Stable Diffusion

I am currently using Kangle Kurnel using Python version 3.7 It kept saying RuntimeError: expected scalar type Float but found Half installed packs accelerate 0.12.0 torch …
조민석
  • 33
  • 5
2
votes
0 answers

Load .ckpt files from CivitAi into pytorch for inference

I've been researching all over for a tutorial/guide to load a civitAI model (https://civitai.com/models/4823/deliberate) into pytorch and then use it for Inference. Most research leads to the following: Create your base model (which should have the…
Vandan Chopra
  • 31
  • 3
2
votes
1 answer

OSError: There was a specific connection error when trying to load CompVis/stable-diffusion-v1-4:

System Info Google Colab, Free version, GPU Information [ ] The official example scripts [X] My own modified scripts Tasks [ ] An officially supported task in the examples folder (such as GLUE/SQuAD, ...) [X] My own task or dataset (give details…
sogu
  • 2,738
  • 5
  • 31
  • 90
2
votes
1 answer

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0, not self coding a program

I'm at the end of my rope. I don't know anything about coding, I don't know how to fix this, I'm not even trying to code a program, and I am getting this while trying to create a token using automatic1111's textual inversion method. Not training it,…
Armads
  • 41
  • 1
  • 4
1
vote
1 answer

adetailer in post request payload for stable diffusion api

I need to use adetailer in post request payload for stable diffusion (SD), but i can't find how to insert it in post payload. Don't find any method in SD API documentation. Please help. Here is my paylaod to post request (commented - we try it but…
Roman Zakharov
  • 11
  • 2
1
vote
1 answer

Stable Diffusion can't connect to the server running inside docker

I built a docker image based on stable-diffusion-webui and after the container started I wouldn't be able to access the web server inside the docker. I entered the docker image and make sure the server is working: $ docker exec -it d29e04e6ca24…
Winston
  • 1,308
  • 5
  • 16
  • 34
1
vote
0 answers

How to convert .safetensors or .ckpt Files and Using in FlaxStableDiffusionImg2ImgPipeline?

I am trying to convert a .safetensors model to a diffusers model using the Python script found at https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py. The command I tried is python3…
Aero Wang
  • 8,382
  • 14
  • 63
  • 99
1
vote
1 answer

I am unable to download the Sagemaker file "Response entity too large"

I'm using SageMaker Studio Lab and trying to download a file that's 2GB large. Unfortunately, I get the error Response entity too large. I don't know how to make the server allow the download of a large file. A friend said that I could split the…
Anna Annie
  • 11
  • 2
1
vote
0 answers

Stable Diffusion/Automatic1111 EC2 server passing status checks but the Elastic IP refuses connection

I am attempting to create a Stable Diffusion server with the Automatic1111 web UI on AWS EC2 using this article. The CloudFormation template launched without error. Via EC2 instance connect, I used sudo nano setup.sh to write the startup script to…
Nathaniel Lindsey
  • 125
  • 6
1
vote
0 answers

"SadTalker" is running solely on my CPU instead of utilizing the GPU

"SadTalker", an extension of stable diffusion, is running solely on my CPU instead of utilizing the GPU I am using two arguments in the 'webui-user.bat' file: --medvram and --disable-safe-unpickle. It doesn't work without the --disable-safe-unpickle…
Katy Brown
  • 11
  • 1
1
vote
0 answers

NansException, Pytorch, Vram and Memory : A Stable Diffusion fairy tale

I started Stable Diffusion with EasyDiffusion. Nice tool, but not enough for my needs. Automatic1111's WebUI got my attention quickly, and then here I am. Started using it a bit, and it works perfectly for simple gens. Although, I'd like to…
Shalvus
  • 15
  • 6
1
vote
2 answers

CUDA available in notebook but not in VS code terminal - same conda environment

I have torch installed in a conda environment. When I run python in command line and try to check CUDA availability I get False as show below. >>> import torch >>> torch.cuda.is_available() False However, when I use jupyter notebook, it shows CUDA…
kamal tanwar
  • 197
  • 8
1
2
3
…
13 14