hesw23168's picture
Update README.md
f94f1c6
metadata
license: openrail

General model coming soon.

Anime model is custom mix + finetune on dataset of high quality images (mix including Anything 4.0, WD 1.4 Booru, Seek Art Mega V1) and contains the contains the kl-f8-anime2 VAE from Waifu Diffusion.

Example settings/prompt:

highres, best quality, 1girl, europe, tulips, solo, flower, hat, day, braid, dress, outdoors, field, freckles, brown hair, brown eyes, long hair, long sleeves, open mouth, looking at viewer Negative prompt: (lowres:1.1), (worst quality:1.2), (low quality:1.1), bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, normal quality, jpeg artifacts, signature, watermark, username, blurry Steps: 23, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 2602542608, Size: 512x576, Model hash: 219cd98caf, Batch size: 2, Batch pos: 1, Denoising strength: 0.67, Clip skip: 2, ENSD: 31337, Hires upscale: 1.5, Hires steps: 14, Hires upscaler: Latent (antialiased)

Example images from anime model:

awiog.jpg