|
|
|
--- |
|
license: creativeml-openrail-m |
|
base_model: kandinsky-community/kandinsky-2-2-decoder |
|
prior: |
|
- ECLIPSE-Community/Lambda-ECLIPSE-Prior-v1.0 |
|
tags: |
|
- λ-ECLIPSE |
|
- ECLIPSE |
|
- kandinsky |
|
- text-to-image |
|
- diffusers |
|
inference: true |
|
--- |
|
|
|
# Finetuning - mpatel57/backpack_dog |
|
|
|
This pipeline was finetuned from **kandinsky-community/kandinsky-2-2-decoder**. Below are some example images generated with the finetuned pipeline using the following prompts: ['A dog']: |
|
|
|
 |
|
|
|
|
|
Note: these example images should not follow the original target concept!! This is to ensure that there is not overfitting. |
|
## Pipeline usage |
|
|
|
## Training info |
|
|
|
These are the key hyperparameters used during training: |
|
|
|
* Epochs: 200 |
|
* Learning rate: 1e-05 |
|
* Batch size: 1 |
|
* Gradient accumulation steps: 4 |
|
* Image resolution: 768 |
|
* Mixed-precision: None |
|
|
|
|
|
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/apg-cogint/text2image-fine-tune/runs/pkv8k94o). |
|
|
