Instructions to use amd/Micro-World-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/Micro-World-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/Micro-World-2", 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
Download action/config.json from amd/Micro-World-2: direct link, hf CLI and curl.
- Browser
- Download file 497 Bytes
-
https://huggingface.co/amd/Micro-World-2/resolve/main/action/config.json
- Command line
-
hf download hf://amd/Micro-World-2/action/config.json
-
curl -L -o config.json https://huggingface.co/amd/Micro-World-2/resolve/main/action/config.json
497 Bytes
| { | |
| "_class_name": "CausalWanActionAdaLNModel", | |
| "_diffusers_version": "0.34.0", | |
| "action_dim": 1536, | |
| "cross_attn_norm": true, | |
| "dim": 3072, | |
| "eps": 1e-06, | |
| "ffn_dim": 14336, | |
| "freq_dim": 256, | |
| "in_channels": 16, | |
| "in_dim": 48, | |
| "keyboard_dim": 7, | |
| "model_type": "ti2v", | |
| "mouse_dim": 2, | |
| "num_heads": 24, | |
| "num_layers": 30, | |
| "out_dim": 48, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm": true, | |
| "text_dim": 4096, | |
| "text_len": 512, | |
| "window_size": [ | |
| -1, | |
| -1 | |
| ] | |
| } |