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
0 answers
Stable Diffusion ControlNet returning Failed to infer
I'm trying to run ControlNet for Stable Diffusion, on my Mac M1.
Here's the code I'm running
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
import torch
import PIL.Image as Image
checkpoint =…
Ulto 4
- 368
- 4
- 16
0
votes
0 answers
NameError: name 'model' is not defined
I'm trying to render a video input in Stable Diffusion (on the Google Colab v0.5), but when I try to run the program, it says NameError: name 'model' is not defined.
I've tried looking for solutions on this website but I don't understand them; I'm…
Koen ter Braak
- 1
- 1
0
votes
0 answers
AttributeError: Can't pickle local object 'main..preprocess_train'
https://huggingface.co/docs/diffusers/training/lora
I am trying to use this code to lora train,My simplified code goes like this:
accelerate launch --mixed_precision="fp16" examples/text_to_image/train_text_to_image_lora.py…
0
votes
0 answers
Running Stable Diffusion image generation in Docker container
I'm trying to write a little service that generates some StableDiffusion images. It is a simple FastAPI application with a Celery queue running in a docker container with access to a GPU. When running the application outside of the docker container…
Redman_plus
- 1
- 1
0
votes
0 answers
Getting an error when I try to use Stable Diffusion with miniconda3
Today I searched online for a way to get an AI Image Generator on my own PC. So far I followed every step, that I found on an online article. Up until the point, where I input, what kind of image I wanted to create. After I entered the desired…
JB24
- 1
0
votes
0 answers
Fine-tuning ImageNet diffusion model on unconditional/conditional data
I want to fine tune some generative diffusion model (DDPM), lets say trained on ImageNet (NOT Stable Diffusion which is text2img), to some other data like CelebA or CIFAR-10. I wonder two things:
does my pretrained model needs to be unconditional?…
alpk
- 43
- 5
0
votes
0 answers
How to input negative prompt with FlaxStableDiffusionImg2ImgPipeline when using diffusers?
prompt = "masterpiece, best quality, 1girl, at dusk"
neg_prompt = "(low quality, worst quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2)"
num_samples =…
Aero Wang
- 8,382
- 14
- 63
- 99
0
votes
2 answers
How to use civitAI checkpoint with ControlNet
I am in the early stage of learning Stable Diffusion.
Motivation:
I would like to generate real object picture from line art like this.
I found that I need to use ControlNet. However, when I download majicMIX realistic. It does not support…
joe
- 8,383
- 13
- 61
- 109
0
votes
0 answers
I'm trying to install stable difussion in Mac. Error installing gfpgan. Preparing metadata (pyproject.toml): finished with status 'error'
When I'm trying to install stable diffusion in Mac, I've followed the tutorial until the part in installing gfpgan.
I'm a complete beginner in coding, so I'm not sure what's going on.
Preparing metadata (pyproject.toml): started
Preparing…
0
votes
1 answer
How to show the output from a request's response from a huggingface text to image API?
import requests
from PIL import Image
API_URL = "https://api-inference.huggingface.co/models/runwayml/stable-diffusion-v1-5"
headers = {"Authorization": f"Bearer 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"}
def query(payload):
response =…
Naresh Gusain
- 1
- 1
0
votes
0 answers
Loading A Stable Diffusion/Dreambooth Model Without Retraining On Google Collab
I'm using the following Google Colab notebook to train a Stable Diffusion (Dreambooth?) model. After a period of inactivity, the Google Colab notebook disconnects. Is there a way to resurrect the session from the saved model checkpoint file saved in…
02fentym
- 1,762
- 2
- 16
- 29
0
votes
1 answer
Stable Diffusion error (not a git repository)
when launching webui.bat, the error
venv "M:\\stable-diffusion-webui-master (1)\\stable-diffusion-webui-master\\venv\\Scripts\\Python.exe"
fatal: not a git repository (or any of the parent directories): .git
first there were errors 9009, then…
root228q
- 11
- 1
- 1
0
votes
1 answer
How to apply LORAs like in SD WebUI to DreamShaper using python
I have been using stable diffusion WebUI to try out different models and LORAs for my application. I'm trying to now do the equivalent of what I've been doing in WebUI but in Python. I have a safetensors file for DreamShaper v5 beta-2 with VAE baked…
Day Trip
- 51
- 12
0
votes
0 answers
How can I add a checkpoint path from Gdrive to continue training in shivamshrirao repo on Colab?
How to continue training from a checkpoint in shivamshrirao repo on Colab?
Where am I supposed to add the checkpoint path from Gdrive?
!python3 train_dreambooth.py
--pretrained_model_name_or_path=$MODEL_NAME…
Hussein
- 1
0
votes
0 answers
NameError when trying to run Huggingface Diffuser Tutorial
I'm going through the Huggingface diffuser tutorial (https://huggingface.co/docs/diffusers/main/en/tutorials/basic_training) and am running into an issue when trying to run the model.
Error:
╭─────────────────────────────── Traceback (most recent…
Gamma1
- 21
- 1
- 3