Instructions to use krasnova/ddim_afhq_64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use krasnova/ddim_afhq_64 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krasnova/ddim_afhq_64", 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
Inference fail
#1
by zituitui - opened
hi
thanks for your work! But I try this checkpoint for DDPMPipeline, PNDMLMPipeline, and DDIMPipeline, these all result in noise images.
Could you indicate possible reasons? I use diffusers 0.20.0.dev0.
Best regards!
Hello,
Thanks for your interest :)
It was part of my thesis where I trained models by myself and compared performance. This model was trained on 50 epochs, you also can find the model that was trained on 20 epochs in my repo.
First one (50 epochs) indeed produces noisy images, whereas the latter produce something that look like animals
great thanks for your reply! I will try that 20 epoch one.
Best regards.
