Questions tagged [stable-diffusion]
Stable Diffusion is a generative AI art engine created by Stability AI. Use this tag for programming or code-writing questions related to Stable Diffusion. Non-programming questions, such as general use or installation, are off-topic.
stable-diffusion
271
questions
0
votes
0
answers
45
views
Stable Diffusion 3 does not work with diffusers
I try to use Stable Diffusion 3 on my desktop.
But it doesn't work.
I make the test.py file, the file is mostly same as sample code on Hugging Face.
Difference is only about authentication. The sample ...
- 1
-2
votes
0
answers
25
views
How to make adapter_conditioning_scale trainable in multiple T2I_Adapter? [closed]
Below is the code using Multi T2I_Adapter. As seen in the code below, adapter_conditioning_scale=[0.8, 0.8], is manually set.
adapters = MultiAdapter(
[
T2IAdapter.from_pretrained("...
- 49
0
votes
0
answers
9
views
How to use ComfyUI for running stable diffusion models?
I wan to know if there is a way in which without much GPU utilization, one can use ComfyUI for garment imposition on another image.
I have until now watched few YT videos but most of them are ...
- 33
0
votes
0
answers
15
views
Saving KerasCV StableDiffusion model locally for reuse later on
I am using keras_cv.models.StableDiffusion to generate images from text and has the following code:
import keras_cv
import keras
import matplotlib.pyplot as plt
from PIL import Image
def plot_images(...
- 177
0
votes
1
answer
162
views
Upgrading to Stable Diffusion 3 from 2-1 on mac
I'm upgrading my stable diffusion from 2-1 to stable-diffusion-3-medium-diffusers
Here is my code which is working for version 2-1
# source venv/bin/activate
from diffusers import DiffusionPipeline
...
- 1,739
0
votes
0
answers
64
views
Stable diffusion three no unet being passed
Hi I am trying to use stable diffusion three when using the StableDiffusionPipeline but get the error of.
It is missing the unet attribute
Pipeline <class 'diffusers.pipelines.stable_diffusion....
0
votes
0
answers
19
views
latent diffusion - Unet: Sizes of tensors must match except in dimension 1
I'm training latent diffusion with audio encoding of shape batch 16 * channel 256 * n_frame 501 * n_frequency 6.
Traceback (most recent call last):
File "/home/szding/.pycharm_helpers/pydev/...
- 73
0
votes
0
answers
58
views
How to inpaint a product seamlessly without generating background image from a prompt in Stable Diffusion?
I want to create good Images of cars. I have empty garage background image which I want to use for every car.
My users would upload car images with random background. I want to remove that background ...
- 3,180
0
votes
0
answers
77
views
Error after downgrading from python 3.12.3 to 3.10.6
I was trying to play with stable diffusion and installed py3.12.3(latest) , after an issue arose I saw that someone recommended downgrading to py3.10.6.
I ran webui-user.bat (not important, this is ...
0
votes
0
answers
18
views
How to get the grad of input image of StableDiffusionXLControlNetPipeline
I have another model to generate the input image of StableDiffusionXLControlNetPipeline, and I used the loss based on the output of StableDiffusionXLControlNetPipeline, I want my model can get the ...
- 1
0
votes
2
answers
150
views
How to Fine-Tune Pre-Trained Stable Diffusion Models Using Custom Images
I am utilizing Stable Diffusion XL Base 1.0 for image generation, but it does not accept my custom input image. I would like to generate a new image based on my input image and the specified prompt.
I ...
1
vote
0
answers
40
views
The pre-trained model stabilityai/stable-diffusion-xl-refiner-1.0 is not working on when giving input image
the issue is that when giving the input image to the stabilityai/stable-diffusion-xl-refiner-1.0 model then it is not taking the given image rather than that model is creating the image according to ...
0
votes
0
answers
64
views
I want to create API for stable diffusion outpainting
Here is what I tried and it did not worked, I want to create some solution that will enable me to connect to my stable dyffusion model, send a img there and "make that img bigger"/outpaint ...
- 235
0
votes
0
answers
17
views
Safety filter SD models
Whenever I access Hugginface's Stable Diffusion models via ComfiUI, the models are lacking a safety filter; meaning they will generate harmful content, which does not happen if I use the code snipped ...
user25290276
0
votes
0
answers
81
views
Stable Diffusion A1111: Difference Between sampler_name and sampler_index in img2img and txt2img Payload Parameters
I am using Stable Diffusion A1111 for img2img and txt2img tasks, and I have encountered two payload parameters: sampler_name and sampler_index. What are the functions of these two parameters, and what ...
- 86