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

..

sd_vae_approx.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_fal.py

RUF013 updates and formatting

2026-03-24 06:07:34 -07:00

sd_vae_natten.py

unified logger

2026-02-19 09:46:42 +01:00

sd_vae_ostris.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_remote.py

fix model/vae: wrong quant_config var, getattr guards, remote-vae latent_copy shadowing + response handling

2026-06-12 13:00:39 -04:00

sd_vae_repa.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_stablecascade.py

pylint

2026-02-19 11:36:20 +01:00

sd_vae_taesd.py

feat(krea2): add Krea 2 (K2) image model support

2026-06-23 04:41:54 +01:00