Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
thumbnail: "https://huggingface.co/Norod78/sd15-caricature-portraits-blip-captions/resolve/main/example/IMG_9234_cunet_anime_noise0.jpg"
|
| 6 |
+
tags:
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- stable-diffusion-diffusers
|
| 9 |
+
- text-to-image
|
| 10 |
+
datasets:
|
| 11 |
+
- Norod78/caricature-portraits-blip-captions-512
|
| 12 |
+
inference: true
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Caricature portraits diffusion model
|
| 16 |
+
*Stable Diffusion v1.5 fine tuned on the 2D Caricature Dataset from [3D-CariGAN](https://github.com/qq775193759/3D-CariGAN) cropped to 512x512 and blip captioned
|
| 17 |
+
|
| 18 |
+
If you want more details on how to generate your own blip cpationed dataset see this [colab](https://colab.research.google.com/gist/Norod/ee6ee3c4bf11c2d2be531d728ec30824/buildimagedatasetwithblipcaptionsanduploadtohf.ipynb)
|
| 19 |
+
|
| 20 |
+
Training was done using this Hugging-Face's text to image training [script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py)
|
| 21 |
+
|
| 22 |
+
## About
|
| 23 |
+
|
| 24 |
+
Put in a text prompt and generate caricatures
|
| 25 |
+
|
| 26 |
+
## AUTOMATIC1111 webui checkpoint
|
| 27 |
+
|
| 28 |
+
The [main](https://huggingface.co/Norod78/sd15-caricature-portraits-blip-captions/tree/main) folder contains a .safetensors file to be put in [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) "stable-diffusion-webui/models/Stable-diffusion" folder and used to generate images
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
## Dataset and Training
|
| 33 |
+
|
| 34 |
+
Finetuned for 10,000 iterations upon [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on [BLIP captioned portraits portraits](https://huggingface.co/datasets/Norod78/caricature-portraits-blip-captions-512) using 1xA5000 GPU on my home desktop computer
|
| 35 |
+
|
| 36 |
+
Trained by [@Norod78](https://twitter.com/Norod78)
|
| 37 |
+
|
| 38 |
+
## Theb original Caricature dataset citation credits
|
| 39 |
+
```
|
| 40 |
+
@article{ye2021caricature,
|
| 41 |
+
author = {Ye, Zipeng and Xia, Mengfei and Sun, Yanan and Yi, Ran and Yu, Minjing and Zhang, Juyong and Lai, Yu-Kun and Liu, Yong-Jin},
|
| 42 |
+
title = {3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos},
|
| 43 |
+
journal = {IEEE Transactions on Visualization and Computer Graphics},
|
| 44 |
+
year = {2021},
|
| 45 |
+
doi={10.1109/TVCG.2021.3126659},
|
| 46 |
+
}
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|