Instructions to use zghhui/Meissonic_MaskFocus_HPS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zghhui/Meissonic_MaskFocus_HPS with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zghhui/Meissonic_MaskFocus_HPS", 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 Settings
- Draw Things
- DiffusionBee
Download config.json from zghhui/Meissonic_MaskFocus_HPS: direct link, hf CLI and curl.
- Browser
- Download file 451 Bytes
-
https://huggingface.co/zghhui/Meissonic_MaskFocus_HPS/resolve/main/config.json
- Command line
-
hf download hf://zghhui/Meissonic_MaskFocus_HPS/config.json
-
curl -L -o config.json https://huggingface.co/zghhui/Meissonic_MaskFocus_HPS/resolve/main/config.json
451 Bytes
| { | |
| "_class_name": "Transformer2DModel", | |
| "_diffusers_version": "0.30.2", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "codebook_size": 8192, | |
| "downsample": true, | |
| "guidance_embeds": false, | |
| "in_channels": 64, | |
| "joint_attention_dim": 1024, | |
| "num_attention_heads": 8, | |
| "num_layers": 14, | |
| "num_single_layers": 28, | |
| "patch_size": 1, | |
| "pooled_projection_dim": 1024, | |
| "upsample": true, | |
| "vocab_size": 8256 | |
| } | |