Instructions to use joachimsallstrom/Double-Exposure-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joachimsallstrom/Double-Exposure-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("joachimsallstrom/Double-Exposure-Diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
double exposure don't work anymore ?
Hello, when I discovered the double exposure model, everything was working perfectly. I come back to it today and it's impossible to make double exposure models: for example, if I put man galaxy, it no longer looks like it used to, like your example. Is there a problem recently because given my 1660 gtx graphics card, I cannot switch to 2x embedding
Hello, when I discovered the double exposure model, everything was working perfectly. I come back to it today and it's impossible to make double exposure models: for example, if I put man galaxy, it no longer looks like it used to, like your example. Is there a problem recently because given my 1660 gtx graphics card, I cannot switch to 2x embedding
Hi! You came back to it by loading it up again with Auto1111? If you have had it on your computer before and just started it all up again, the only thing that I can say could be the issue is that you updated Auto and that makes it fail. Also look over that you use the right trigger word and settings overall that you did before. Hope it works!
In trigger keyword, I tried dublex and dublex style. The problem didn't exist before the "drama" automatic 1111. No doubt it is indeed a problem due to a web ui update. However, I specify that it is the double exposure effect that does not work: I have an image but no longer the effect that the model is supposed to provide