Text-to-Image
Diffusers
Safetensors
prism-dit
diffusion
dit
flow-matching
rectified-flow
artistic
custom-architecture
Instructions to use WZRD-AI/PRISM-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WZRD-AI/PRISM-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WZRD-AI/PRISM-1", 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
Download config.json from WZRD-AI/PRISM-1: direct link, hf CLI and curl.
- Browser
- Download file 475 Bytes
-
https://huggingface.co/WZRD-AI/PRISM-1/resolve/main/config.json
- Command line
-
hf download hf://WZRD-AI/PRISM-1/config.json
-
curl -L -o config.json https://huggingface.co/WZRD-AI/PRISM-1/resolve/main/config.json
475 Bytes
| { | |
| "_class_name": "PrismDiT", | |
| "model_type": "prism-dit", | |
| "architecture": "PrismDiT", | |
| "in_channels": 16, | |
| "out_channels": 16, | |
| "patch_size": 2, | |
| "hidden_size": 1152, | |
| "depth": 28, | |
| "num_heads": 16, | |
| "mlp_ratio": 4.0, | |
| "context_dim": 1024, | |
| "diffusion_type": "flow-matching", | |
| "scheduler": "PrismFlowScheduler", | |
| "recommended_sampler": "Euler", | |
| "recommended_steps": "12-25", | |
| "recommended_cfg": "5.0-6.5", | |
| "torch_dtype": "float16", | |
| "version": "1.0.0" | |
| } | |