Instructions to use wabibito/Krea2-Onyx-Edit-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wabibito/Krea2-Onyx-Edit-mlx-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("wabibito/Krea2-Onyx-Edit-mlx-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - MLX
How to use wabibito/Krea2-Onyx-Edit-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Krea2-Onyx-Edit-mlx-4bit wabibito/Krea2-Onyx-Edit-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Draw Things
- DiffusionBee
- Atomic Chat
| Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing. | |
| MODIFICATIONS: this repository does NOT contain the Krea Model as released. It is a | |
| Derivative Model created by Onyx (wabibito): the weights of krea/Krea-2-Turbo were quantized to 4-bit MLX with the conradlocke/krea2-identity-edit adapter (v1.2 r64) fused into the weights. | |
| This is an unofficial community build. It is not an official Krea product and is not | |
| endorsed by or affiliated with Krea.ai, Inc. | |
| Use is governed by the Krea 2 Community License Agreement, a copy of which is | |
| distributed with this repository as LICENSE.pdf and published at https://krea.ai/krea-2-licensing. | |
| By downloading or using these weights you agree to be bound by that Agreement, | |
| including its prohibited-use restrictions, its content-filtering requirements for | |
| deployments, and its terms on Commercial Use. | |
| Credits: Krea.ai, Inc. (base model) - conradlocke (identity-edit adapter, | |
| https://huggingface.co/conradlocke/krea2-identity-edit) - face/head/person-swap | |
| skill trained on stablellama's MIT-licensed change_eye_face_head_person dataset. | |