---
license: creativeml-openrail-m
base_model: kandinsky-community/kandinsky-2-2-decoder
datasets:
- AhmetTek41/logo
prior:
- kandinsky-community/kandinsky-2-2-prior
tags:
- kandinsky
- text-to-image
- diffusers
- diffusers-training
inference: true
---
    
# Finetuning - AhmetTek41/output

This pipeline was finetuned from **kandinsky-community/kandinsky-2-2-decoder** on the **AhmetTek41/logo** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A logo for a zero waste club featuring a simple image of a closed loop of arrows, with each arrow made from different recyclable materials like paper, plastic, and metal.']: 

![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("AhmetTek41/output", torch_dtype=torch.float16)
prompt = "A logo for a zero waste club featuring a simple image of a closed loop of arrows, with each arrow made from different recyclable materials like paper, plastic, and metal."
image = pipeline(prompt).images[0]
image.save("my_image.png")
```

## Training info

These are the key hyperparameters used during training:

* Epochs: 77
* Learning rate: 1e-05
* Batch size: 16
* Gradient accumulation steps: 1
* Image resolution: 512
* Mixed-precision: None


More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/ahmetberketekin-kocaeli-university/text2image-fine-tune/runs/b6yh1o8b).