Done for the JVC community, mix of Bastard v4 and AbyssOrangeMix with the MBW extention.
Just a "starter pack" model, don't really overthink it.
Best vae to use is "vae-ft-mse-840000-ema-pruned.vae.pt" uploaded with the model.
Parameters:
Steps: 10 minimum.
Size : 512x512 minimum.
Highres x2, ~30 step is absolutely beautiful, ~0.65 denoising strengh
Best Method : Eular A, DPM ++ 2M Karras
Generic negative prompt:
Anime: portrait, zoomed, soft light, closeup, fake, deformed, extra limbs, extra fingers, mutated hands, bad anatomy, bad proportions, blind, bad eyes, ugly eyes, dead eyes, blur, vignette, out of shot, out of focus, gaussian, closeup, monochrome, grainy, noisy, ((text)), ((writing)), ((logo)), oversaturation, over saturation, overshadow, censorship, ugly, deformed, amateur, odd, fat, lowres, bad anatomy, bad hands, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, ((signature)), ((watermark)), username, blurry, out of focus, bad hands, poorly drawn hands, (((multiple views:1.4))) photorealistic, realistic
Realistic: portrait, zoomed, smooth skin, closeup, cartoon, deformed, extra limbs, extra fingers, mutated hands, bad anatomy, bad proportions, blind, bad eyes, blur, vignette, out of shot, out of focus, gaussian, closeup, monochrome, grainy, noisy, ((text)), ((writing)), ((logo)), censorship, ugly, old, deformed, odd, tall, anime, cell shading, lowres, bad anatomy, bad hands, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, jpeg artifacts, ((signature)), ((watermark)), blurry, out of focus, bad hands, poorly drawn hands, (((multiple views:1.4)))
EDIT 26/01/23 : I got unpublished, but without reason, idk why. File is safe (safetensors) and I merged them myself. Staff, please contact me if anything is wrong with the model, and I will work on it. Thanks you!
KheyouMix [1b8b712d80] is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user undi. Derived from the powerful Stable Diffusion (SD 1.5) model, KheyouMix [1b8b712d80] has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that KheyouMix [1b8b712d80] is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, realistic.
With a rating of 4 and over 1 ratings, KheyouMix [1b8b712d80] is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of KheyouMix [1b8b712d80] from here.
To use KheyouMix [1b8b712d80], download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like KheyouMix [1b8b712d80], check out our crash course in AI image generation.