README.md

---
base_model: neonforestmist/Clover-Image-Tiny
library_name: diffusers
license: creativeml-openrail-m
inference: true
datasets:
  - neonforestmist/GPT_Monet_Style_Images
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - lora
  - clover-image
---

# Clover Image Tiny — Monet LoRA

A rank-16 style LoRA trained on
[`neonforestmist/GPT_Monet_Style_Images`](https://huggingface.co/datasets/neonforestmist/GPT_Monet_Style_Images)
for [`neonforestmist/Clover-Image-Tiny`](https://huggingface.co/neonforestmist/Clover-Image-Tiny).

Use the prompt trigger **`Monet Style`**.

```python
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "neonforestmist/Clover-Image-Tiny",
    torch_dtype=torch.float16,
).to("cuda")
pipe.load_lora_weights("neonforestmist/clover-image-tiny-monet-lora")

image = pipe(
    "Monet Style, a small blue cat resting beside a lily pond",
    num_inference_steps=20,
    guidance_scale=7.5,
).images[0]
```

## Examples

![Validation sample 0](./image_0.png)
![Validation sample 1](./image_1.png)
![Validation sample 2](./image_2.png)
![Validation sample 3](./image_3.png)

## Training

- Base revision: `63b0e9f6be9c00888ff464f342a9ef052bf76681`
- Dataset revision: `2941a88e5268bbb4224ff2916013b78ec313d03a`
- Resolution: 512 × 512
- Optimizer steps: 1,000
- Rank: 16
- Batch size: 1
- Learning rate: 1e-4 with cosine decay and 100 warmup steps
- Min-SNR gamma: 5
- Precision: fp16
- Seed: 20260730
- Trainer: Diffusers 0.39.0 `train_text_to_image_lora.py`

The reproducible job configuration is included in the Clover source
repository under `training/`.

## License and limitations

These adapter weights are a derivative of Clover Image Tiny and use the
CreativeML Open RAIL-M license. The training dataset is Apache-2.0. Generated
content can inherit limitations and biases from the base checkpoint and
training data; review outputs before use.