Instructions to use Rin247/Hunyuan3D-Part with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/Hunyuan3D-Part with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Rin247/Hunyuan3D-Part", 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 model/config.json from Rin247/Hunyuan3D-Part: direct link, hf CLI and curl.
- Browser
- Download file 856 Bytes
-
https://huggingface.co/Rin247/Hunyuan3D-Part/resolve/main/model/config.json
- Command line
-
hf download hf://Rin247/Hunyuan3D-Part/model/config.json
-
curl -L -o config.json https://huggingface.co/Rin247/Hunyuan3D-Part/resolve/main/model/config.json
856 Bytes
| { | |
| "target": "partgen.models.partformer_dit.PartFormerDITPlain", | |
| "params": { | |
| "use_self_attention": true, | |
| "use_cross_attention": true, | |
| "use_cross_attention_2": true, | |
| "use_bbox_cond": false, | |
| "num_freqs": 8, | |
| "use_part_embed": true, | |
| "valid_num": 50, | |
| "input_size": 1024, | |
| "in_channels": 64, | |
| "hidden_size": 2048, | |
| "encoder_hidden_dim": 1024, | |
| "encoder_hidden2_dim": 1024, | |
| "depth": 21, | |
| "num_heads": 16, | |
| "qk_norm": true, | |
| "qkv_bias": false, | |
| "qk_norm_type": "rms", | |
| "with_decoupled_ca": false, | |
| "decoupled_ca_dim": 4096, | |
| "decoupled_ca_weight": 1.0, | |
| "use_attention_pooling": false, | |
| "use_pos_emb": false, | |
| "num_moe_layers": 6, | |
| "num_experts": 8, | |
| "moe_top_k": 2 | |
| } | |
| } |