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
0
votes
1 answer
How to read Stable Diffusion Prompt from meta data in PNG file in C#
I tried the bitmap class and the information stored in PropertyItems doesn't appear to have any stable diffusion prompt information (eve if the Id isn't 0x0010). Any help would be appreciated.
using (var image = new Bitmap(imagePath))
…
Philip
- 147
- 7
0
votes
1 answer
Stable Diffusion Text Inversion Training: cv2.error when using Auto Focal Point
Anyone recognize this error? New SD build and running latest opencv (4.8.0). I have no idea how to even fix this?
File "C:\Users\Logi\Documents\stable-diffusion-webui\modules\textual_inversion\autocrop.py", line 150, in image_face_points
faces =…
Andy H
- 11
0
votes
0 answers
How do I change things in the Stable Diffusion WebUI html and scrips?
I'm still learning in the world of web development and would like to alter the WebUI of stable diffusion: https://github.com/AUTOMATIC1111/stable-diffusion-webui
I know it should be possible to change around or delete buttons etc, but I don't know…
Rezarak SL
- 67
- 8
0
votes
0 answers
stable diffusion sometimes generates images with weird lines
When I generate image with huggingface stable diffusion pipeline, it sometimes generate with weird green, yellow and red lines as shown in the picture.
Is anyone who knows the reason of this, and how I can remove this lines?
To reproduce :
model_id…
puhuk
- 464
- 5
- 15
0
votes
0 answers
Bypassing GPU Requirement for a conversion script (ckpt to safetensor)
I'm trying to use this code in a virtual environment
# Got a bunch of .ckpt files to convert?
# Here's a handy script to take care of all that for you!
# Original .ckpt files are not touched!
# Make sure you have enough disk space! You are going to…
0
votes
0 answers
While installing mcube module using pip install, I am getting below error even if I have installed CS C++ build tool 14
Processing c:\users\kunal saxena\stable-dreamfusion\pymcubes
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Collecting numpy (from PyMCubes==0.1.4)
Downloading…
0
votes
0 answers
AttributeError: 'numpy.ndarray' object has no attribute 'map'
AttributeError: 'numpy.ndarray' object has no attribute 'map'`
I don't know shape of tensorflow datasets. So might be it's not compatible with my own datasets.
i got the code from KERAS https://keras.io/examples/generative/ddpm/.
i want to use own…
Maju Perut
- 1
- 1
0
votes
0 answers
How to incorporate Frechet Inception Distance into latent diffusion training and valiadation in pytorch lightning?
I am using stable diffusion code to train a diffusion model. Their paper mentioned FID scores assessed on 5000 samples using 100 DDIM steps. The git repository does not have the implementation for how they computed the FID score over 5000 samples. I…
bananagator
- 551
- 3
- 8
- 26
0
votes
0 answers
Need help getting "ERROR: Exception:" when trying to start weubui-use
Keep getting this error below
Error: ExceptionAlready up to date.
I've already delete the venv folder and install using python 3.10.6 version
I have try delete everything and reinstall stable diffusion, but keep getting the same error.
I have no…
Fong122
- 1
0
votes
0 answers
How to fine tune text encoder for training a stable diffusion model with dreambooth?
I am trying to train the model for a specific art with few images and I see that stable diffusion 1.5 is getting poor results for prompts, mostly the faces are messed up.
I tried another checkpoint from hugging face which is using the same stable…
nayan dhabarde
- 1,734
- 1
- 19
- 38
0
votes
0 answers
Error using dreambooth on collab: HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name
currently trying to run dreambooth on google collab with another model - https://huggingface.co/Lykon/DreamShaper
everything seems to run okie however in the last step: PART 3.0: Configure and load your model, ready to create AI images, when i run…
Chirag verma
- 313
- 2
- 16
0
votes
0 answers
Why relative import is not useful in python?
I am downloading the stable-diffusion 2.0
when I use
python script/txt2img.py
got an unexpected error:
ModuleNotFoundError: No module named 'ldm'
i have the same problem in sd-v1.5,but to change the code in txt2img i got successfully
from
from…
black_cat
- 30
- 5
0
votes
1 answer
Path not found when running webui-user.bat
I am trying to install Stable diffusion for my machine but everytime I run "webui-user.bat" it tells me
venv "C:\Users\user\Desktop\Stable Diffusion\stable-diffusion-webui\venv\Scripts\Python.exe"
Path not found
and when I check the "venv" file,…
Jimpsoni
- 233
- 2
- 13
0
votes
1 answer
ValueError and OSError when attempting to install and run Stable Diffusion
Was attempting to install and run Stable Diffusion on my local machine via these instructions. Got to the section where I'm testing out the model to see if it runs and I get this:
(ldm) C:\stable-diffusion\stable-diffusion-main>python…
Alditrus
- 87
- 1
- 5
0
votes
0 answers
Stable diffusion API: copied code from documentation just to practice generating an image on nuxt3, and i keeping a CORS error. How to fix?
Im using nuxt 3 and I'm basing my code off of this documentation:
https://stablediffusionapi.com/docs/stable-diffusion-api/text2img/
Im just trying to change this image tag's source into whatever the api gives me. Everything is in…
Daniel Awoke
- 1
- 1