Instructions to use fishze/Refacade with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fishze/Refacade with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fishze/Refacade", 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": "VaceMMModel", | |
| "_diffusers_version": "0.30.0", | |
| "dim": 1536, | |
| "dim_ref": 1536, | |
| "eps": 1e-06, | |
| "ffn_dim": 8960, | |
| "ffn_dim_ref": 8960, | |
| "freq_dim": 256, | |
| "in_dim": 16, | |
| "model_type": "t2v", | |
| "num_heads": 12, | |
| "num_layers": 30, | |
| "out_dim": 16, | |
| "text_len": 256, | |
| "vace_layers": [0, 5, 10, 15, 20, 24, 28], | |
| "vace_in_dim": 96, | |
| "ref_in_dim": 80 | |
| } | |