Model reference · open weights
Krea-2 is an open-weight image model from krea. Krea-2-Turbo (BF16) weighs 35.7 GB; the smallest configuration that runs it is L40S 48 GB.
Summary of the krea/Krea-2-Turbo model card, 2026-10-01
What it is
| Released by | krea |
|---|---|
| Released | 2026-06-18 |
| Parameters | 12.8B |
| VRAM | 35.7 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB | does not fit | |
| L40S 48 GB | tight | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Krea-2: Text to Image: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “Krea-2: Text to Image” (17.8 GB)
get Comfy-Org/Krea-2 diffusion_models/krea2_turbo_fp8_scaled.safetensors diffusion_models
get Comfy-Org/Krea-2 text_encoders/qwen3vl_4b_fp8_scaled.safetensors text_encoders
get Comfy-Org/Krea-2 vae/qwen_image_vae.safetensors vae
get Comfy-Org/Krea-2 loras/krea2_darkbrush.safetensors loras
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT