Instructions to use ovedrive/Krea-2-Raw-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ovedrive/Krea-2-Raw-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ovedrive/Krea-2-Raw-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "A small, dark-colored cat is captured mid-stride, walking down the center of a narrow, abandoned street. The street is paved and appears cracked and worn. On either side of the street are tall, dilapidated buildings with visible brickwork and windows. A street lamp stands on the right side. The entire image is rendered in a monochromatic blue, with a distinct halftone dot pattern overlaying the scene, giving it a retro or printed appearance. The focus is soft, and the lighting is diffused, creating a hazy, atmospheric effect. The perspective is from ground level, looking down the length of the street, which narrows into the distance., halftone texture" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| { | |
| "quantization_method": "mixed_precision_nf4", | |
| "model_type": "krea", | |
| "description": "First and last blocks plus boundary modules kept at bfloat16, middle layers quantized to NF4 (krea architecture)", | |
| "high_precision_layers_count": 56, | |
| "removed_stale_checkpoint_indexes": [ | |
| "transformer/diffusion_pytorch_model.safetensors.index.json" | |
| ] | |
| } |