stable-diffusion
stable-diffusion copied to clipboard
CompVis
A latent text-to-image diffusion model
Hello everyone! Thanks for your great project and for your job! I have are little question. Do you have any guides about fine tuning for stable diffusion?
I've been writing an interactive version of txt2img.py that minics the behaviour of the discord bot. What I can't figure out is how to retrieve the individual random seeds for...
```sh (ldm) hugo@DESKTOP:/mnt/d/stable-diffusion$ python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms --ckpt models/ldm/text2img256/model.ckpt Global seed set to 42 Loading model from models/ldm/text2img256/model.ckpt Global Step: 947666 LatentDiffusion:...
Am I just really underestimating the complexity of running this?
Am I missing it? Is it possible to use commands to increase the Width and Height?
https://huggingface.co/CompVis/stable-diffusion-v-1-3/discussions/1 I did some fixes and it is able to generate images on colab PRO Please, feel free to improve the notebook 10 minutes installation 40 seconds to generate 6...
This looks like an interesting project; however, my limited understanding of your licensing appears to make the code unusable for 3rd parties. Perhaps it's just incomplete? :) Any chance you...
Wanted to try sampling on cpu but can't get it to work. Are there any solutions for this problem? RuntimeError: Expected all tensors to be on the same device, but...
Hi Team, I want to try training the model in 16-bit precision. It looks that the code does not support it yet. Plus, I wonder if you have some comments...
