Downloads · 30 days
1.2K
28% of all-time downloads
scat-krea2-v1
uviol/scat-krea2-v1
scat-krea2-v1 is a text-to-image model from uviol. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
Scat LoRA. Use natural language, "shitting" was the preferred verb. Only trained on photos so far, style LoRAs are probably necessary for non-realism.
All-time downloads
4.1K
Public
Repo size
235 MB
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors235 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Jun 30, 2026
- SHA
- 08eafde5
Base models
Model card
From the Hugging Face model README
Scat LoRA — Krea 2
Model description
Scat LoRA. Use natural language, "shitting" was the preferred verb. Only trained on photos so far, style LoRAs are probably necessary for non-realism.
Training info
v1
Dataset
Same dataset as Klein-9B version.
Hyperparameters
| Parameter | Value |
|---|---|
| Base model | Krea-2-Raw |
| Trainer | musubi-tuner |
| Dim/Rank | 16 |
| Optimizer | AdamW8Bit (defaults) |
| LR Schedule | cosine_with_min_lr |
| LR | 2e-4 |
| Min LR ratio | 0.1 |
| Warmup steps | 300 |
| Epochs | 120 (12240 steps) |
| Timestep Sampling | krea2_shift |
Download model
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Created
- Jun 30, 2026
- Updated
- Jun 30, 2026