Yuzus goal are easy to archive high quality images with a style that can range from anime to light semi realistic (where semi realistic is the default style). Be aware that some prompts can push it more to realism like "detailed". If faces apear more near the viewer, it also tends to go more realistic.Baked in VAE is <a target="_blank" rel="ugc" href="https://civarchive.com/models/22354?modelVersionId=26816">clearvae_variant. </a>You can also use <a target="_blank" rel="ugc" href="https://civarchive.com/models/23906/kl-f8-anime2-vae">klF8Anime2</a>, to push the colors, but eyes can get blurry.My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. If you'd like to support my work, you can do so at: <a target="_new" rel="ugc" href="https://subscribestar.adult/citrus-models">SubscribeStar</a>, every bit helps and is truly appreciated!____________________________________________________________ Supporters:Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna_____________________________________________________Using the model:Use mostly <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">danbooru</a> tags. No extra vae needed. For better promting on it, use this <a target="_blank" rel="ugc" href="https://aituts.com/novelai-anime-prompt-techniques/">LINK</a> or <a target="_blank" rel="ugc" href="https://lunarmimi.net/freebies/novelai-anime-girl-prompt-guide/#1basic">LINK</a>. But instead of {}, use (), <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">stable-diffusion-webui</a> use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative.My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.Use clip skip 1 or 2 with sampler DPM++ 2M Karras or DDIM. I use clip 2.Don't use face restore and underscores _, type red eyes and not red_eyes.

Yuzu

Biggest change, it is a bit more realistic. What is better:- Better constructed backgrounds and clothes (on most occations)- Hands are slitly betterWhat is better/worse for some:- a bit more realistic, mostly noticeable on the eyes (a bit smaller in compare) with more visible nostrils.Tested on clip2 with mostly CFG Scale 7 to 8

yuzu_v11.safetensors

v1.1

v1.0

Yuzus goal are easy to archive high quality images with a style that can range from anime to light semi realistic (where semi realistic is the default style). Be aware that some prompts can push it more to realism like "detailed". If faces apear more near the viewer, it also tends to go more realistic.My <a rel="ugc noopener noreferrer nofollow" href="https://discord.gg/zSR5FcYWWE" target="_blank">Discord</a> for everything related to anime models and art. You can support me on my <a rel="ugc noopener noreferrer nofollow" href="https://www.patreon.com/user?u=27247323" target="_blank">patreon</a> and if you are interested, we also have a collaboration of multiple AI artists named <a rel="ugc noopener noreferrer nofollow" href="https://www.patreon.com/Ikena" target="_blank">Sinful Sketch Society </a>that you can support!Baked in VAE is <a rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/22354?modelVersionId=26816" target="_blank">clearvae_variant. </a>You can also use <a rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/23906/kl-f8-anime2-vae" target="_blank">klF8Anime2</a>, to push the colors, but eyes can get blurry.Supporters:Thanks to my supporters Riyu, SETI, Jelly, lawrencium_Lr103, Alessandro and Kodokuna on my <a rel="ugc noopener noreferrer nofollow" href="https://patreon.com/user?u=27247323&amp;utm_medium=clipboard_copy&amp;utm_source=copyLink&amp;utm_campaign=creatorshare_creator&amp;utm_content=join_link" target="_blank">patreon</a>!You can support me on my <a rel="ugc noopener noreferrer nofollow" href="https://patreon.com/user?u=27247323&amp;utm_medium=clipboard_copy&amp;utm_source=copyLink&amp;utm_campaign=creatorshare_creator&amp;utm_content=join_link" target="_blank">patreon</a>, where you can get early access to newer model versions._____________________________________________________Using the model:Use mostly <a rel="ugc noopener noreferrer nofollow" href="https://danbooru.donmai.us/" target="_blank">danbooru</a> tags. No extra vae needed. For better promting on it, use this <a rel="ugc noopener noreferrer nofollow" href="https://aituts.com/novelai-anime-prompt-techniques/" target="_blank">LINK</a> or <a rel="ugc noopener noreferrer nofollow" href="https://lunarmimi.net/freebies/novelai-anime-girl-prompt-guide/#1basic" target="_blank">LINK</a>. But instead of {}, use (), <a rel="ugc noopener noreferrer nofollow" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui" target="_blank">stable-diffusion-webui</a> use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative.My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.Use clip skip 1 or 2 with sampler DPM++ 2M Karras or DDIM. I use clip 2.Don't use face restore and underscores _, type red eyes and not red_eyes.

Biggest change, it is a bit more realistic.

What is better:

- Better constructed backgrounds and clothes (on most occations)

- Hands are slitly better

What is better/worse for some:

- a bit more realistic, mostly noticeable on the eyes (a bit smaller in compare) with more visible nostrils.

Tested on clip2 with mostly CFG Scale 7 to 8

Files with SHA256: bdda7b9930e178b9c4c8a66bbb098918352fc8334aa2281162df0c9acf7dd801