|
|
|
--- |
|
license: creativeml-openrail-m |
|
base_model: kandinsky-community/kandinsky-2-2-decoder |
|
datasets: |
|
- ChoudharyTAlhaArain/web-kadi-2.0 |
|
prior: |
|
- kandinsky-community/kandinsky-2-2-prior |
|
tags: |
|
- kandinsky |
|
- text-to-image |
|
- diffusers |
|
- diffusers-training |
|
inference: true |
|
--- |
|
|
|
# Finetuning - ChoudharyTAlhaArain/kadsinky-web-decoder-3.1 |
|
|
|
This pipeline was finetuned from **kandinsky-community/kandinsky-2-2-decoder** on the **ChoudharyTAlhaArain/web-kadi-2.0** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['update web ui/ux']: |
|
|
|
 |
|
|
|
|
|
## Pipeline usage |
|
|
|
You can use the pipeline like so: |
|
|
|
```python |
|
from diffusers import DiffusionPipeline |
|
import torch |
|
|
|
pipeline = AutoPipelineForText2Image.from_pretrained("ChoudharyTAlhaArain/kadsinky-web-decoder-3.1", torch_dtype=torch.float16) |
|
prompt = "update web ui/ux" |
|
image = pipeline(prompt).images[0] |
|
image.save("my_image.png") |
|
``` |
|
|
|
## Training info |
|
|
|
These are the key hyperparameters used during training: |
|
|
|
* Epochs: 116 |
|
* Learning rate: 1e-05 |
|
* Batch size: 1 |
|
* Gradient accumulation steps: 4 |
|
* 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/tanveer-talha-github/text2image-fine-tune/runs/u24l8tl8). |
|
|
