3D, 2.5D, Semi-realistic, Anime, this checkpoint was originally a highly stylized model. Version 2.0 further enhances the style and color contrast. It's expected to be even darker, allowing for more impressive images.
Fast V3：With the addition of oil painting elements, oil painting + 3D should be very cool...，DMD2 has been incorporated to accelerate image generation, saving you some computing power. With 6 steps, you can get an image. Adding LoRa takes 10-16 steps, and there's barely any improvement in quality above 20 steps.
My go-to settings: 20 steps, CFG 2, dpmpp_sde sampler, beat scheduler, 832x1536 resolution.
V1V2：Steps: 20-40, CFG scale: 4-7, Sampler: dpmpp_sde/Euler a/dpmpp2m_sde, scheduler: beat/karras/sgm_uniform/exponential
My usual settings are: 25, 6, dpmpp_sde, beat, 832x1536,
The VAE is already integrated
use size larger than1024x1024 for the original dimensions.
Prompt words and Danbooru tags are the key to making the most of all Illustrious and NOOB features. Everyone, give it a try. Have a great time!