Instructions to use OzzyGT/krea2_reference_blocks with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OzzyGT/krea2_reference_blocks with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OzzyGT/krea2_reference_blocks", 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 modular_config.json from OzzyGT/krea2_reference_blocks: direct link, hf CLI and curl.
- Browser
- Download file 237 Bytes
-
https://huggingface.co/OzzyGT/krea2_reference_blocks/resolve/main/modular_config.json
- Command line
-
hf download hf://OzzyGT/krea2_reference_blocks/modular_config.json
-
curl -L -o modular_config.json https://huggingface.co/OzzyGT/krea2_reference_blocks/resolve/main/modular_config.json
237 Bytes
| { | |
| "_class_name": "Krea2TurboReferenceAutoBlocks", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "auto_map": { | |
| "ModularPipelineBlocks": "krea2_reference.Krea2TurboReferenceAutoBlocks" | |
| }, | |
| "requirements": { | |
| "sdnq": ">=0.2.0" | |
| } | |
| } | |