Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- keras
|
| 5 |
+
- diffusers
|
| 6 |
+
- stable-diffusion
|
| 7 |
+
- text-to-image
|
| 8 |
+
- diffusion-models-class
|
| 9 |
+
- keras-sprint
|
| 10 |
+
- keras-dreambooth
|
| 11 |
+
- scifi
|
| 12 |
+
inference: true
|
| 13 |
+
widget:
|
| 14 |
+
- text: a drawing of drawbayc monkey as a turtle
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# KerasCV Stable Diffusion in Diffusers 🧨🤗
|
| 18 |
+
|
| 19 |
+
DreamBooth model for the `drawbayc monkey` concept trained by nielsgl on the `nielsgl/bayc-tiny` dataset, images from this [Kaggle dataset](https://www.kaggle.com/datasets/stanleyjzheng/bored-apes-yacht-club).
|
| 20 |
+
It can be used by modifying the `instance_prompt`: **a drawing of drawbayc monkey**
|
| 21 |
+
|
| 22 |
+
## Description
|
| 23 |
+
|
| 24 |
+
The pipeline contained in this repository was created using a modified version of [this Space](https://huggingface.co/spaces/sayakpaul/convert-kerascv-sd-diffusers) for StableDiffusionV2 from KerasCV. The purpose is to convert the KerasCV Stable Diffusion weights in a way that is compatible with [Diffusers](https://github.com/huggingface/diffusers). This allows users to fine-tune using KerasCV and use the fine-tuned weights in Diffusers taking advantage of its nifty features (like [schedulers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/schedulers), [fast attention](https://huggingface.co/docs/diffusers/optimization/fp16), etc.).
|
| 25 |
+
This model was created as part of the Keras DreamBooth Sprint 🔥. Visit the [organisation page](https://huggingface.co/keras-dreambooth) for instructions on how to take part!
|
| 26 |
+
|
| 27 |
+
## Examples
|
| 28 |
+
|
| 29 |
+
> A drawing of drawbayc monkey dressed as an astronaut
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
> A drawing of drawbayc monkey dressed as the pope
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
## Usage
|
| 39 |
+
|
| 40 |
+
```python
|
| 41 |
+
from diffusers import StableDiffusionPipeline
|
| 42 |
+
|
| 43 |
+
pipeline = StableDiffusionPipeline.from_pretrained('nielsgl/dreambooth-bored-ape')
|
| 44 |
+
image = pipeline().images[0]
|
| 45 |
+
image
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
## Training hyperparameters
|
| 49 |
+
|
| 50 |
+
The following hyperparameters were used during training:
|
| 51 |
+
|
| 52 |
+
| Hyperparameters | Value |
|
| 53 |
+
| :-- | :-- |
|
| 54 |
+
| name | RMSprop |
|
| 55 |
+
| weight_decay | None |
|
| 56 |
+
| clipnorm | None |
|
| 57 |
+
| global_clipnorm | None |
|
| 58 |
+
| clipvalue | None |
|
| 59 |
+
| use_ema | False |
|
| 60 |
+
| ema_momentum | 0.99 |
|
| 61 |
+
| ema_overwrite_frequency | 100 |
|
| 62 |
+
| jit_compile | True |
|
| 63 |
+
| is_legacy_optimizer | False |
|
| 64 |
+
| learning_rate | 0.0010000000474974513 |
|
| 65 |
+
| rho | 0.9 |
|
| 66 |
+
| momentum | 0.0 |
|
| 67 |
+
| epsilon | 1e-07 |
|
| 68 |
+
| centered | False |
|
| 69 |
+
| training_precision | float32 |
|