A LoRA for Stable Diffusion 1.5 checkpoints, trained to mimic the art style of Hideyuki Tanaka. Hideyuki Tanaka is a 3D designer, animator, character designer and founder of FrameGraphics. He is known for his surreal, colorful, and contemporary illustrations; he is the character designer for Metro's Bust-A-Groove/Bust-A-Move video game series and the designer and director of Super Milk Chan. Trained on about a hundred pictures of Tanaka's work, both 2D illustrations and 3D models.

Usage Tips

• The trigger word is "hwhideyukitanaka".

• Use AbyssOrangeMix3 for best results. Most standard NAI-based checkpoints should be compatible with the LoRA, but this checkpoint seems to render the style with the most accuracy.

• Use Booru language when prompting.

• LoRA strength should be 0.8 to 1.0.

• DPM++ SDE at 512x768 base resolution. Hires fix is not required.

• Optionally use certain tags to emphasize the style; try "solid oval eyes" and/or "flat color" in your prompt.

Remarks

• Stable Diffusion XL/Pony versions are on my bucket list; I don't have enough VRAM to train these LoRA types yet. Be patient!

• It's ideal to use img2img, inpainting and controlnet techniques to get good images, you won't get perfect images from generations alone.

w e l o v e m u s i c ~ !!