Instructions to use mit-han-lab/svdq-int4-flux.1-schnell with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mit-han-lab/svdq-int4-flux.1-schnell with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mit-han-lab/svdq-int4-flux.1-schnell", 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
| { | |
| "model_class": "FluxSchnell", | |
| "model_config": { | |
| "axes_dim": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "context_in_dim": 4096, | |
| "depth": 19, | |
| "depth_single_blocks": 38, | |
| "disable_unet_model_creation": true, | |
| "guidance_embed": false, | |
| "hidden_size": 3072, | |
| "image_model": "flux", | |
| "in_channels": 16, | |
| "mlp_ratio": 4.0, | |
| "num_heads": 24, | |
| "out_channels": 16, | |
| "patch_size": 2, | |
| "qkv_bias": true, | |
| "theta": 10000, | |
| "vec_in_dim": 768 | |
| } | |
| } |