Instructions to use xyhzzzh/SpatialGen-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xyhzzzh/SpatialGen-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xyhzzzh/SpatialGen-1.0", 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
| { | |
| "architectures": [ | |
| "RayMapEncoder" | |
| ], | |
| "image_size": 512, | |
| "in_channel": 6, | |
| "inter_dims": 384, | |
| "model_type": "ray_map_encoder", | |
| "out_channel": 16, | |
| "patch_size": 8, | |
| "torch_dtype": "float16", | |
| "transformer_dim_head": 64, | |
| "transformer_heads": 6, | |
| "transformer_layers": 1, | |
| "transformer_mlp_dim": 384, | |
| "transformers_version": "4.51.3" | |
| } | |