--- license: other thumbnail: >- https://s3.amazonaws.com/moonup/production/uploads/6305db1fcfbde33ef7d480ff/AWS1FulVrdoZGB-WIejqQ.jpeg datasets: - p1atdev/pvc language: - en library_name: diffusers tags: - stable-diffusion - safetensors widget: - text: >- pvc, masterpiece, best quality, exceptional, 1girl, red hair, cat ears, red eyes, curly hair, long hair, maid costume, frills, upper body, looking at viewer, red flowers, indoors, beautiful view, medieval, example_title: PVC - text: >- figma, masterpiece, best quality, best aesthetic, 1girl, cat ears, blue hair, high ponytail, parted bangs, white shirt, dress shirt, short sleeves, shorts, looking at viewer, example_title: Figma - text: >- nendoroid, masterpiece, best quality, best aesthetic, 1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt, example_title: Nendoroid - text: >- pvc, masterpiece, best quality, best aesthetic, 1girl, bangs, bare shoulders, beret, black hair, black shorts, blue hair, bracelet, breasts, buttons, colored inner hair, double-breasted, eyewear removed, green headwear, green jacket, grey eyes, grey sky, hat, jacket, jewelry, long hair, looking at viewer, multicolored hair, neck ring, o-ring, off shoulder, rain, round eyewear, shorts, sidelocks, small breasts, solo, sunglasses, wavy hair, wet, zipper, example_title: Green jacket pipeline_tag: text-to-image --- # PVC v4 This model is a latent diffusion model finetuned on Waifu Diffusion v1.5 beta 2.6 with PVC figure images. You can use Danbooru tags to generate images. ## Downloads
Please use [WD's vae](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt) to get good results! ## Prompt guide **Highres fix is highly recommended.** ### Trigger words - `pvc` means the pvc material style but not needed always. - `figma` is the figure style that has joints, and more tend to be product thumbnail images. To get joints, please emphasize `figma` by 1.2 ~ 1.5 or use `doll joints` tag. - `nendoroid` means the style of chibi figures. Use with `chibi` to get better chibis. ### Negative prompt ``` (worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, cropped, signature, blurry ``` ## Comparison to v3 ![sample-diff-1](https://huggingface.co/p1atdev/pvc-v4/resolve/main/images/sample-diff-1.jpg) ``` masterpiece, best quality, best aesthetic, 1girl, red hair, cat ears, closed eyes, closed mouth, expressionless, maid costume, apron, lolita dress, frills, lying on back, sheets, red flowers, from above Negative prompt: (worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, error, cropped, jpeg artifacts, signature, watermark, username, blurry Steps: 18, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1166304922, Size: 512x768, Model hash: 0866b17d46, Model: pvc-v3-fp16, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires steps: 12, Hires upscaler: Latent ``` ## Examples TODO: あとでやる ## Training informationParameter | Value |
---|---|
Service | Runpod |
GPU | A4500 |
Script | kohya-ss/sd-scripts |
Cost | about $10 |
Hours | about 30 hours |
Dataset | about 18000 images from p1atdev/pvc |
Resolution | 768 |
Epochs | 13 |
Optimizer | Lion |
LR | 1e-7 |
Scheduler | cosine_with_restarts |
Train Batch Size | 12 |