---
license: mit
base_model: warp-ai/wuerstchen-prior
datasets:
- dongOi071102/meme-pretreatment-dataset
tags:
- wuerstchen
- text-to-image
- diffusers
- diffusers-training
- lora
inference: true
---
    
# LoRA Finetuning - dongOi071102/wuerstchen-prior-meme-lora-4

This pipeline was finetuned from **warp-ai/wuerstchen-prior** on the **dongOi071102/meme-pretreatment-dataset** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['a catton cat with angry face']: 

![val_imgs_grid](./val_imgs_grid.png)


## Pipeline usage

You can use the pipeline like so:

```python
from diffusers import DiffusionPipeline
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
                "warp-ai/wuerstchen", torch_dtype=float32
            )
# load lora weights from folder:
pipeline.prior_pipe.load_lora_weights("dongOi071102/wuerstchen-prior-meme-lora-4", torch_dtype=float32)

image = pipeline(prompt=prompt).images[0]
image.save("my_image.png")
```

## Training info

These are the key hyperparameters used during training:

* LoRA rank: 4
* Epochs: 100
* Learning rate: 0.0001
* Batch size: 8
* Gradient accumulation steps: 1
* Image resolution: 512
* Mixed-precision: fp16


More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/2111818-no/text2image-fine-tune/runs/xmsqasc9).