Update README.md

README.md

@@ -10,4 +10,53 @@ tags:
 - safetensors
 ---
 
-# PVC
+# PVC
+
+![eyecatch](https://huggingface.co/p1atdev/pvc/resolve/main/samples/miku.png)
+
+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.
+You can use Danbooru tags to generate.
+
+# Model links
+
+- [**pvc-v1.safetensors**](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1.safetensors)
+- [**pvc-v1.ckpt**](https://huggingface.co/p1atdev/pvc/resolve/main/pvc-v1.ckpt)
+- [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))
+
+# Samples
+
+![sample1](https://huggingface.co/p1atdev/pvc/resolve/main/samples/sample1.png)
+
+```
+masterpiece, best quality, 1girl, green hair, sweater, beanie, turtleneck, looking at viewer,
+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
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
+```
+
+---
+
+![sample2](https://huggingface.co/p1atdev/pvc/resolve/main/samples/sample2.png)
+
+
+```
+masterpiece, best quality, 1girl, smile, black hair, long hair, school uniform, navel, pleated skirt, leaning forward, looking at viewer, wind
+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,
+Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 10
+```
+
+---
+
+![sample3](https://huggingface.co/p1atdev/pvc/resolve/main/samples/sample3.png)
+
+
+```
+masterpiece, best quality, 1girl, fascinator, hat, victorian, gothic, dress, frills, looking at viewer,
+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
+Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7
+```
+
+# Training information
+
+```
+--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
+```