This is an illustrious anime model, focused on consistent outputs and detailed backgrounds with a painting-like artstyle. It’s pretty easy to control and it will yield good results without many quality tags.V2 should be a decent improvement across the board, it has better prompt adherence, colors and nicer faces. It needs a bit lower CFG than V1.V2alt is just a small style adjustement with some lighting improvements.Short usage guideUse DPM++ 2M SDE, with CFG 2-2.5, 20-40 steps.Hires fix is not required, but ADetailer is probably preferable. Prompts I use two sets of prompts with nearly the similar frequency.<ul><li>First one allows to achieve the best lighting and detail, but not every image really needs it and excessive quality tag prompting can degrade the prompt adherence:</li></ul><pre><code>masterpiece, best quality, amazing quality, very aesthetic, absurdres,newest,detailed face,(volumetric lighting)</code></pre>Negative<pre><code>lowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest,simple background</code></pre><ul><li>Second one is simple, almost pure model output with two quality tags to fix small details:</li></ul><pre><code>masterpiece</code></pre>Negative<pre><code>worst quality</code></pre>For better shadows just add this, maybe also add "solo" if you get shadowy figures, Illustrious does that sometimes:<pre><code>volumetric lighting,shadows</code></pre>Also you can add this in negative as you see fit because I had problems with characters having longer than usual fangs or adetailer adding teeth over lips:<pre><code>fangs,teeth,sharp teeth</code></pre> Base models used in this merge:NoobIEater by jyrrata <a target="_blank" rel="ugc" href="https://civarchive.com/models/879640?modelVersionId=1034051">https://civarchive.com/models/879640?modelVersionId=1034051</a>NTR MIX by tkio <a target="_blank" rel="ugc" href="https://civarchive.com/models/926443?modelVersionId=1061268">https://civarchive.com/models/926443?modelVersionId=1061268</a>

VentusMix

Altered v2 style, better lighting and more depth. CFG 2.

ventusmix_v2alt.safetensors

v2alt

v2.0

v1.0

This is an illustrious anime model, focused on consistent outputs and detailed backgrounds with a painting-like artstyle. It’s pretty easy to control and it will yield good results without many quality tags.V2 should be a decent improvement across the board, it has better prompt adherence, colors and nicer faces. It needs a bit lower CFG than V1.V2alt is just a small style adjustement with some lighting improvements.Short usage guideUse DPM++ 2M SDE, with CFG 2-2.5, 20-40 steps.Hires fix is not required, but ADetailer is probably preferable.Prompts&nbsp;I use two sets of prompts with nearly the similar frequency.<ul><li>First one allows to achieve the best lighting and detail, but not every image really needs it and excessive quality tag prompting can degrade the prompt adherence:</li></ul>masterpiece, best quality, amazing quality, very aesthetic, absurdres,newest,detailed face,(volumetric lighting)Negativelowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest,simple background<ul><li>Second one is simple, almost pure model output with two quality tags to fix small details:</li></ul>masterpieceNegativeworst qualityFor better shadows just add this, maybe also add "solo" if you get shadowy figures, Illustrious does that someties:volumetric lighting,shadowsAlso you can add this in negative as you see fit because I had problems with characters having longer than usual fangs or random sweating:fangs,sweat,sharp teethBase models used in this merge:NoobIEater by jyrrata <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/879640?modelVersionId=1034051">https://civitai.com/models/879640?modelVersionId=1034051</a>NTR MIX by tkio <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/926443?modelVersionId=1061268">https://civitai.com/models/926443?modelVersionId=1061268</a>

Altered v2 style, better lighting and more depth. CFG 2.

Files with SHA256: 00799d755d722129c351af8e701af898a662a0066562657fc0115fe6327e66a0