dt-krea-2

Krea 2 Turbo weights in the Draw Things (s4nnc .ckpt) format, mirrored unmodified from the Draw Things model CDN for use by JoyFusion's on-device inference. The conversion and quantization were done by the Draw Things project; the files here are byte-identical to the upstream ones.

File	Variant	Size	SHA-256
`krea_2_turbo_q8p.ckpt`	8-bit	13,388,873,728	`d5c0771a00fae06a749378b56318a361b8f3aeec42feb617c5486ac0d014dc23`
`krea_2_turbo_q6p.ckpt`	6-bit	10,283,876,352	`fa610a2eb1753739d6855a3b84e55081ca2aa857fdd05f3fd70b7c635560ae5d`
`qwen_3_vl_4b_q8p.ckpt`	text encoder	4,526,047,232	`be71703dbe695d2aee038539ac0a4dcba02a3ffdc4df4e5fe0b2c3f70a47c151`

The VAE qwen_image_vae_f16.ckpt (Qwen-Image, Apache-2.0) lives in JoyFusionAI/dt-components.

License

Krea 2 is licensed under the Krea 2 Community License Agreement (see LICENSE.pdf and NOTICE), which every recipient must accept, together with the Acceptable Use Policy. For more information, visit https://krea.ai/krea-2-licensing.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for JoyFusionAI/dt-krea-2

Base model

krea/Krea-2-Raw

Finetuned

krea/Krea-2-Turbo

Quantized

(45)

this model