Instructions to use wavymulder/Analog-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wavymulder/Analog-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("wavymulder/Analog-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
This is my favorite model from all, period! Need help?
Hi Wayvymulder, can't figure out how to write you directly. I've been enjoying Analog Diffusion a lot, and made true gems with it. Will post them soon. I do have a huge manually curated glamour library of photos. Could we maybe work on this to even make more fine tuned models? Let me know how I could help you on that, I love what you did.
Hello Kayzen, sorry for not responding sooner.
I appreciate the kind offer and kind words! I'm not currently able to take you up on the offer, but I'd love to see the sort of model you could make with that dataset!
I’d just like to weigh in on this—great work wavymulder, you inspired me to go my own route and do something unique in my own dataset. Thanks for the inspiration and the effort.
how to run on windows?