Instructions to use JSYuuu/ThinkGen-stage3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use JSYuuu/ThinkGen-stage3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("JSYuuu/ThinkGen-stage3", 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": "ThinkGenTransformer2DModel", | |
| "_diffusers_version": "0.34.1", | |
| "axes_dim_rope": [ | |
| 40, | |
| 40, | |
| 40 | |
| ], | |
| "axes_lens": [ | |
| 10000, | |
| 10000, | |
| 10000 | |
| ], | |
| "ffn_dim_multiplier": null, | |
| "hidden_size": 2520, | |
| "in_channels": 16, | |
| "multiple_of": 256, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 21, | |
| "num_kv_heads": 7, | |
| "num_layers": 32, | |
| "num_refiner_layers": 2, | |
| "out_channels": null, | |
| "patch_size": 2, | |
| "text_feat_dim": 4096, | |
| "timestep_scale": 1000.0 | |
| } | |