---
license: creativeml-openrail-m
base_model: kandinsky-community/kandinsky-2-2-decoder
datasets:
- lambdalabs/pokemon-blip-captions
prior:
- kandinsky-community/kandinsky-2-2-prior
tags:
- kandinsky
- text-to-image
- diffusers
inference: true
---
    
# Finetuning - YiYiXu/yiyi_kandinsky_decoder

This pipeline was finetuned from **kandinsky-community/kandinsky-2-2-decoder** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A robot pokemon, 4k photo']: 

![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("YiYiXu/yiyi_kandinsky_decoder", torch_dtype=torch.float16)
prompt = "A robot pokemon, 4k photo"
image = pipeline(prompt).images[0]
image.save("my_image.png")
```

## Training info

These are the key hyperparameters used during training:

* Epochs: 2
* Learning rate: 1e-05
* Batch size: 1
* Gradient accumulation steps: 1
* Image resolution: 768
* Mixed-precision: fp16


More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/yiyixu/text2image-fine-tune/runs/znfqqva8).