Krea 2 Onyx Edit mlx 4bit

MLX 4-bit build of Krea 2 with the krea2-identity-edit adapter (v1.2 r64) fused into the weights - zero runtime LoRA cost, streams like a plain checkpoint. Built for the Onyx on-device app: attach a reference photo (plus an optional second for swaps/try-on) and describe the change.

Distilled 8-step base: fast, instruction-faithful - the recommended edit build.

See NOTICE for attribution and LICENSE.pdf for the Krea 2 Community License this model is distributed under.

License

Krea 2 Onyx builds are Derivative Models of Krea 2 and are distributed under the Krea 2 Community License Agreement (LICENSE.pdf in this repository; https://krea.ai/krea-2-licensing). By downloading or using these weights you agree to be bound by that Agreement, including:

  • its prohibited uses and Acceptable Use Policy;
  • the requirement that deployments implement content filters (prompt/output filtering, abuse detection, moderation) to prevent prohibited uses and outputs;
  • its Commercial Use terms (permitted under the Agreement only below the revenue threshold in s2.3; above it, an Enterprise License from Krea is required);
  • passing these same obligations to anyone you redistribute to (s3.1).

This is an unofficial community build - not an official Krea product, and not endorsed by or affiliated with Krea.ai, Inc. See NOTICE for attribution.

Downloads last month
27
Safetensors
Model size
2B params
Tensor type
F16
路
U32
路
BF16
路
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for wabibito/Krea2-Onyx-Edit-mlx-4bit

Base model

krea/Krea-2-Raw
Finetuned
(64)
this model