Instructions to use jiuntian/OneHOI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jiuntian/OneHOI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jiuntian/OneHOI", 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
- Draw Things
- DiffusionBee
| { | |
| "_class_name": "GroundingEncoder", | |
| "_diffusers_version": "0.35.0.dev0", | |
| "fourier_freq": 32, | |
| "hidden_size": 2048, | |
| "init_logit": -5.0, | |
| "max_hoi_seq": 32, | |
| "mlp_out_std": 0.0003, | |
| "n_roles": 3, | |
| "pos_embed_dim": 32, | |
| "role_embed_dim": 32, | |
| "role_std": 0.02, | |
| "text_encoder_dim": 4096 | |
| } | |