Downloads · 30 days
0
krea2-snofs-75
fbbcool/krea2-snofs-75
krea2-snofs-75 is a text-to-image model from fbbcool. Use it when you need an image from a text prompt. The card lists the license as other.
The snofs style adapter merged into comfy-org/krea-2 at strength 0.75.
Access
Public
Updated Jul 3, 2026
Repo size
53.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors53.6 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- other
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- d7424760
Base models
Model card
From the Hugging Face model README
krea2-snofs-75
The snofs style adapter merged into comfy-org/krea-2 at strength 0.75.
The adapter is a full-form LyCORIS LoKr (kron(w1, w2)); the merge adds 0.75 * kron(w1, w2) to each of the 256 targeted linear weights (the stored alpha is inert for full-form LoKr, matching ComfyUI's LoKrAdapter).
Files
| File | Base | Precision | Use |
|---|---|---|---|
krea2-raw-snofs0.75-bf16.safetensors | raw | bf16 | training base (full precision) |
krea2-turbo-snofs0.75-fp8-scaled.safetensors | turbo | fp8_e4m3fn scaled | inference (8-step turbo) |
The fp8 file uses per-tensor scaled fp8 (scale = max|W| / 448, dequant fp8 * scale) with the same _quantization_metadata layout as the stock krea-2 fp8 checkpoints, so it loads natively in ComfyUI.
ComfyUI usage
Load with UNETLoader (no LoRA node — snofs is baked into the weights):
- inference:
krea2-turbo-snofs0.75-fp8-scaled.safetensors, CLIPLoader typekrea2, VAEqwen_image_vae. Turbo: ~8 steps, cfg 1, samplerer_sde, schedulersimple.
- Task
- Text-to-Image
- License
- other
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026