Downloads · 30 days
11
6% of all-time downloads
sammy-style-lora
jayark/sammy-style-lora
sammy-style-lora is a text-to-image model from jayark. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
Style LoRA trained on Qwen-Image-2512 to capture the Sammy children's book art style. Generates new characters, environments, and backgrounds in the style — not limited to any single character.
All-time downloads
170
Public
Repo size
590 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors590 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Apr 9, 2026
- Updated
- Apr 9, 2026
- SHA
- 26a462ff
Model card
From the Hugging Face model README
Sammy Style LoRA
Style LoRA trained on Qwen-Image-2512 to capture the Sammy children's book art style. Generates new characters, environments, and backgrounds in the style — not limited to any single character.
Usage
- Trigger word:
sammy style - Base model: Qwen-Image-2512
- Architecture: LoRA (rank 16, alpha 4)
Checkpoints
| File | Training Step | Notes |
|---|---|---|
sammy-style-400.safetensors | 400 | Earlier checkpoint |
sammy-style-600.safetensors | 600 | Recommended — best quality/fidelity balance |
Training Details
- ~50-70 training images (character images, backgrounds, synthetic fills)
- Natural language captions (not booru tags) — required by Qwen2.5-VL text encoder
- Captions describe content only; style is the learned residual
- 1500 total training steps; step 400-600 is the sweet spot before overfitting
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Created
- Apr 9, 2026
- Updated
- Apr 9, 2026