---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-3-medium
tags:
  - stable-diffusion-3
  - stable-diffusion-3-diffusers
  - text-to-image
  - diffusers
  - lora
inference: true
---

# SD3 LoRA - Tilt-Shift Miniature Photography Style (tsmini)

## Model Details

### Model Description

This is a LoRA adapter trained on Stable Diffusion 3 Medium for the **tilt-shift miniature photography** style. The trigger word is `tsmini`.

- **Developed by:** [Zeta Young]
- **License:** CreativeML OpenRAIL-M
- **Base model:** Stable Diffusion 3 Medium (`stabilityai/stable-diffusion-3-medium-diffusers`)
- **Adapter type:** LoRA (rank=16, alpha=16)

## Training Details

### Training Data

- 26 high-quality tilt-shift miniature photography images
- Style: shallow depth of field, aerial/diorama perspective, miniature effect
- Resolution: 1024×1024

### Training Configuration

| Parameter | Value |
|-----------|-------|
| Training script | `diffusers/examples/dreambooth/train_dreambooth_lora_sd3.py` |
| Instance prompt | "in the style of tsmini" |
| Resolution | 1024 |
| Train batch size | 1 |
| Gradient accumulation steps | 4 |
| Learning rate | 1e-4 |
| LR scheduler | constant |
| Max train steps | 1000 |
| LoRA rank | 16 |
| LoRA alpha | 16 |
| Mixed precision | bf16 |
| Gradient checkpointing | enabled |

### Training Hardware

- 2× NVIDIA RTX 4090 (24GB each)
- Single GPU training (SD3 ~2B params fits on one card)

## How to Use

```python
import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers",
    torch_dtype=torch.bfloat16,
).to("cuda")

# Load LoRA
pipe.load_lora_weights("your-username/sd3-lora-tsmini", weight_name="pytorch_lora_weights.safetensors")

# Generate with style
image = pipe(
    "tsmini, tilt-shift miniature photography, miniature effect, aerial view, shallow depth of field, a city street at sunset with glowing streets",
    num_inference_steps=28,
    guidance_scale=7.0,
    height=1024,
    width=1024,
).images[0]
image.save("output.png")
```

## Results

### LoRA Scale Comparison

| Scale | Quality | Style Strength |
|-------|---------|----------------|
| 0.5 | Good | Weak |
| 0.75 | Good | Moderate |
| **1.0** | **Best** | **Strong** |
| 1.5 | Artifacts appear | Too strong |
| 2.0 | Severe artifacts | Overloaded |

See `eval_images/` folder for full comparison images.

### Observations

- The LoRA successfully transfers the tilt-shift miniature style
- Most effective on: cityscapes, aerial views, scenes with clear depth layers
- Scale > 1.0 causes artifacts (noise, ghosting) — this is inherent to LoRA scaling, not a data quality issue
- Style strength can be adjusted via `pipe.set_adapters(["tsmini"], adapter_weights=[scale])`

## Limitations

- Style effect is subtle on some prompts (e.g., close-up subjects)
- Works best with prompts describing scenes with depth/distance
- Trained on a small dataset (26 images), may not generalize to all scene types

## Key Learnings

1. **Official training scripts > custom scripts** — SD3's multi-encoder + flow matching details are easy to get wrong
2. **Timestep consistency is critical** — flow matching timestep range must match between training and inference
3. **Data quality > data quantity** — 26 consistent-style images sufficient for style LoRA
4. **Upscale doesn't help for style LoRA** — LoRA learns style features, not pixel details