Instructions to use AISkywalker/DDPM_LDM_DDPM_VARIANCE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AISkywalker/DDPM_LDM_DDPM_VARIANCE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AISkywalker/DDPM_LDM_DDPM_VARIANCE", torch_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
| Model,DDPM VARIANCE extra 5000 images added,LDM extra 5000 images added,mixed_data_ldm_0.2,mixed_data_ldm_0.5,mixed_datd_ldm_0.8 | |
| Convnext-Tiny,95.05,91.77,95.05,96.15,97.8 | |
| ResNet-18,92.31,92.41,93.41,95.05,95.05 | |
| Swin-T,94.51,90.51,95.6,93.96,94.51 | |
| ViT-Tiny,90.11,87.97,92.86,90.66,91.76 | |