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
14
Safetensors
Model size
2B params
Tensor type
F16
U32
BF16
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
(25)
this model