Files
automatic/models/Reference
CalamitousFelicitousness 48fad8524e feat(krea2): add Krea 2 (K2) image model support
Krea 2 is a 12.9B single-stream flow-matching DiT trained from scratch, using a Qwen3-VL-4B text encoder and the Qwen-Image VAE. The transformer is vendored as a diffusers ModelMixin whose module tree mirrors the checkpoint, so weights load with no key conversion; the pipeline ports the reference encode, flow-matching denoise, and VAE decode. The text encoder is shared at runtime via the existing dedup registry, so Base and Turbo reuse one Qwen3-VL-4B copy.

Covers text-to-image, image-to-image, native LoRA, and the single-file UNET override. Also completes SD.Next's partial Qwen-Image VAE support (5D decode input and TAESD preview mapping) that K2 shares.
2026-06-23 04:41:54 +01:00
..
2026-04-03 13:12:08 +00:00
2026-04-12 19:06:08 +02:00
2026-04-18 14:34:10 +00:00
2024-05-21 11:42:59 -04:00
2026-02-17 17:12:40 +00:00
2025-10-05 20:17:32 -04:00