Waifu Diffusion 1.3

768x768 safetensors version of this model with the kl-f8-anime2 VAE baked in. It's the no-ema version of wd-v1-3-full.ckpt from https://huggingface.co/hakurei/waifu-diffusion-v1-3 converted by using this method: https://huggingface.co/Yntec/DucHaitenAIart-beta/discussions/4

It's a model hard to prompt that requires a whole circus and the clowns of negative prompts to give good outputs, specially at these resolutions, but it still produces unique images.

Samples and prompts:

Free online image generator Waifu Diffusion v13

(Click for larger)

Top left: face focus, cute, masterpiece, best quality, 1girl, teal hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck

Top right: ((princess_peach)), (anime face), chibi, pink dress, blonde hair, blue eyes, wearing crown, forest by Artgerm

Bottom left: Photo of a gorgeous blonde female in the style of stefan kostic, realistic, half body shot, sharp focus, 8 k high definition, insanely detailed, intricate, elegant, art by stanley lau and artgerm, extreme blur cherry blossoms background

Bottom right: Fantasy landscape of a large majestic castle adorned with gold white marble walls, lots of towers bridges and levels on top of a lush cliff with a huge waterfalls in the middle, ruins at the bottom, afternoon light streaking with god rays, ornate, octane render, 8k, artstation, google images, 35mm lens, detailed matte painting, deep color, fantastical, intricate detail, splash screen, complementary colors, fantasy concept art, 8k resolution trending on Artstation Unreal Engine 5

Downloads last month
1,155
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using Yntec/WaifuDiffusion 26