Text-to-Image
Diffusers
Safetensors
stable-diffusion-xl
z-image
diffusion distillation
one-step generation
rlhf
Instructions to use Junyi-W/DIDR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Junyi-W/DIDR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Junyi-W/DIDR", 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 Settings
- Draw Things
- DiffusionBee
Commit History
11 days ago
-
Link first author to homepage
Verified signatureee75d9e
19 days ago
-
Link paper to arXiv 2605.24001
Verified signature00287b1 -
Point code links to github.com/Junyi-W/DIDR
Verified signature5301eb8 -
Use load_config for UNet (avoid deprecated from_config path)
Verified signature5171a13 -
Use Hanfu portrait prompt for Z-Image example
Verified signaturea910579 -
Add Z-Image DIDR 1-step transformer; finalize usage
Verified signature737a8be -
Set cc-by-nc-4.0 license; separate SDXL DIDR / DIDR-longer usage
Verified signaturea1de96e -
Add model card
Verified signature25e6ab5