Instructions to use SceneWorks/sd3.5-large-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/sd3.5-large-mlx with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SceneWorks/sd3.5-large-mlx", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - MLX
How to use SceneWorks/sd3.5-large-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir sd3.5-large-mlx SceneWorks/sd3.5-large-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Draw Things
- DiffusionBee
| { | |
| "_class_name": "SD3Transformer2DModel", | |
| "_diffusers_version": "0.31.0.dev0", | |
| "attention_head_dim": 64, | |
| "caption_projection_dim": 2432, | |
| "in_channels": 16, | |
| "joint_attention_dim": 4096, | |
| "num_attention_heads": 38, | |
| "num_layers": 38, | |
| "out_channels": 16, | |
| "patch_size": 2, | |
| "pooled_projection_dim": 2048, | |
| "pos_embed_max_size": 192, | |
| "qk_norm": "rms_norm", | |
| "sample_size": 128, | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 64 | |
| } | |
| } |