Instructions to use gatilin/nitrofusion2-dit-refiners with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gatilin/nitrofusion2-dit-refiners with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("gatilin/nitrofusion2-dit-refiners", 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 extraction.json from gatilin/nitrofusion2-dit-refiners: direct link, hf CLI and curl.
- Browser
- Download file 640 Bytes
-
https://huggingface.co/gatilin/nitrofusion2-dit-refiners/resolve/main/extraction.json
- Command line
-
hf download hf://gatilin/nitrofusion2-dit-refiners/extraction.json
-
curl -L -o extraction.json https://huggingface.co/gatilin/nitrofusion2-dit-refiners/resolve/main/extraction.json
640 Bytes
| { | |
| "source_repo": "ChenDY/NitroFusion2", | |
| "source_revision": "62d1a7000af9c46a0c4348d936bd7670ff33c1b9", | |
| "source_shards": [ | |
| "diffusion_pytorch_model-00001-of-00003.safetensors" | |
| ], | |
| "scope": "noise_refiner.* and context_refiner.* (the two 2-layer refiner stacks of the Z-Image MMDiT; the 30-layer trunk, embedders and final layer are excluded)", | |
| "naming": "original checkpoint tensor names preserved", | |
| "tensor_count": 56, | |
| "tensor_bytes": 1431492608, | |
| "parameters": 715746304, | |
| "sha256": "c871ae336b02e763a4be2018231a1b616082fd4edb04a51189b2798dcfb62284", | |
| "source_range_bytes_verified": true, | |
| "license": "Apache-2.0" | |
| } | |