Instructions to use DavyMorgan/tiny-sd35-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DavyMorgan/tiny-sd35-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DavyMorgan/tiny-sd35-pipe", 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": "SD3Transformer2DModel", | |
| "_diffusers_version": "0.32.0.dev0", | |
| "attention_head_dim": 8, | |
| "caption_projection_dim": 32, | |
| "dual_attention_layers": [ | |
| 0, | |
| 1 | |
| ], | |
| "in_channels": 8, | |
| "joint_attention_dim": 32, | |
| "num_attention_heads": 4, | |
| "num_layers": 4, | |
| "out_channels": 8, | |
| "patch_size": 1, | |
| "pooled_projection_dim": 64, | |
| "pos_embed_max_size": 96, | |
| "qk_norm": "rms_norm", | |
| "sample_size": 32 | |
| } | |