Unconditional Image Generation
Diffusers
Safetensors
RAEDiTPipeline
rae
rae-dit
diffusion-transformer
imagenet-256
arxiv:2510.11690
Instructions to use plugyawn/rae-dit-s-ep14-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use plugyawn/rae-dit-s-ep14-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("plugyawn/rae-dit-s-ep14-diffusers", 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
| { | |
| "_class_name": "RAEDiT2DModel", | |
| "_diffusers_version": "0.38.0.dev0", | |
| "_name_or_path": "/tmp/tmppwg9zch4/transformer", | |
| "class_dropout_prob": 0.1, | |
| "depth": [ | |
| 12, | |
| 2 | |
| ], | |
| "hidden_size": [ | |
| 384, | |
| 2048 | |
| ], | |
| "in_channels": 768, | |
| "mlp_ratio": 4.0, | |
| "num_classes": 1000, | |
| "num_heads": [ | |
| 6, | |
| 16 | |
| ], | |
| "patch_size": 1, | |
| "sample_size": 16, | |
| "use_pos_embed": true, | |
| "use_qknorm": false, | |
| "use_rmsnorm": true, | |
| "use_rope": true, | |
| "use_swiglu": true, | |
| "wo_shift": false | |
| } | |