Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,53 @@ tags:
|
|
| 10 |
- safetensors
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# PVC
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- safetensors
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# PVC
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
This model is a latent diffusion model finetuned on [Waifu Diffusion v1.4 epoch 2](https://huggingface.co/hakurei/waifu-diffusion-v1-4) with [PVC figure images](https://huggingface.co/datasets/p1atdev/pvc) using LoRA method.
|
| 18 |
+
You can use Danbooru tags to generate.
|
| 19 |
+
|
| 20 |
+
# Model links
|
| 21 |
+
|
| 22 |
+
- [**pvc-v1.safetensors**](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1.safetensors)
|
| 23 |
+
- [**pvc-v1.ckpt**](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1.ckpt)
|
| 24 |
+
- [pvc-v1-lora.pt](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1-lora.pt) (maybe only works with kohya's [sd-scripts](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1-lora.pt) or [webui extension](https://github.com/kohya-ss/sd-webui-additional-networks))
|
| 25 |
+
|
| 26 |
+
# Samples
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
```
|
| 31 |
+
masterpiece, best quality, 1girl, green hair, sweater, beanie, turtleneck, looking at viewer,
|
| 32 |
+
Negative prompt: nsfw, worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
|
| 33 |
+
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
```
|
| 42 |
+
masterpiece, best quality, 1girl, smile, black hair, long hair, school uniform, navel, pleated skirt, leaning forward, looking at viewer, wind
|
| 43 |
+
Negative prompt: nsfw, worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry,
|
| 44 |
+
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 10
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
```
|
| 53 |
+
masterpiece, best quality, 1girl, fascinator, hat, victorian, gothic, dress, frills, looking at viewer,
|
| 54 |
+
Negative prompt: worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, censored, hetero
|
| 55 |
+
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
# Training information
|
| 59 |
+
|
| 60 |
+
```
|
| 61 |
+
--train_batch_size 1 --resolution 768,768 --learning_rate 1e-4 --max_train_steps 17740 --use_8bit_adam --xformers --mixed_precision fp16 --save_every_n_epochs 1 --network_module networks.lora --v2 --enable_bucket --max_token_length 225 --network_dim 16 --text_encoder_lr 5e-5
|
| 62 |
+
```
|