<h3 id="(capable-of-a-wide-range-of-styles-from-flat-to-simi-realism).">(Capable of a wide range of styles, from flat to simi-realism).</h3>Please Rate! - Your feedback, ratings or a follow are greatly appreciated. - Thankyou!I used a face detailer in many of the example images, and most use upscaling (4x-nickelback). A face detailer is generally helpful depending on zoom level, If your subjects face is about 30% or more of the image it can be detrimental and cause loss of detail. I urge experimentation in all areas, adjust settings accordingly.V2 - BaselineI normally wouldn't publish a new version so quickly, but V1 felt a bit undercooked and sterile to me. I consider this a bit of a fix, It is a bit more toon biased, but prompting can still yield a wide range of styles. (See below for settings / v1 settings still apply).V1 - BroadstrokeSuggested settings:<ul><li>VAE: sdxl_vae (baked in)</li><li>Clip skip: 2 was used during merge, (setting 1 or 2 should yield same results)</li><li>Sampler: Euler Ancestral - SGM Uniform (most consistent good results). (more testing needed regarding additional samplers).</li><li>Resolution: all standard 1MP resolutions work well in portrait and landscape, (depending on context) (I often use 1024x1360 and 1120x1440 in portrait and landscape)</li><li>CFG: 2.8 - 9.0 (lower for more realism, (generally) - I commonly use 3.8, 5 ,7&amp;9)</li><li>Steps: 22 - 36(I use 26 most often)</li></ul>Prompting:Primarily <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">Danbooru</a> tags, mixed with a bit of natural language prompting. (look to my sample images for examples and general formatting).<pre><code>number of characters (1girl/1boy), character name, artist prompt, scene/environment/camera angle, action, expression, items, quality prompts (masterpiece, best quality)</code></pre><ul><li>negative prompts - lowres, worst quality, (it can be helpful to add a few things like "toon, illustration, unreal", if you're pushing for greater realism). (Additionally you can try the opposite I.E. adding photorealism to your neg prompt will give you a more flat / anime look).</li></ul><h3 id="resources-used-creator-thanks">Resources used / Creator thanks</h3>Checkpoints:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1767712/fabled-infusion-illustrious-xl-hybrid-nsfw?modelVersionId=2000557https://civarchive.com/models/1767712/fabled-infusion-illustrious-xl-hybrid-nsfw">Fabled Infusion v1</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/prodajie">self, (prodajie)</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1162518?modelVersionId=1714002">Plant Milk - Walnut</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/Ocean3">Ocean3</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl?modelVersionId=1761560">WAI-NSFW v14</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/WAI0731">WAI0731</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/140272/hassaku-xl-illustrious?modelVersionId=2010753">Hassaku XL v3.0</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/Ikena">Ikena</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1110783/ilustmix">iLustMix v7.0</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/GZees">GZees</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/507472?modelVersionId=1413921">Uncanny valley ilxl10Noob</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/meden">meden</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/36281/toonify">Toonify IL</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/BetterThanNothing">BetterThanNothing</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1661037/nexora-spectrum-of-limitless-style">Nexora Prism</a> by <a target="_blank" rel="ugc" href="https://civarchive.com/user/ArvoraVisio">ArvoraVisio</a>(Additionally, thanks to everyone whos prompts I've pilfered for testing).

Chromesthesia

I was unhappy with some of the outputs I was getting with the 1st version. It was a bit sterile without the right prompts. Version 2 adds more style and dynamic composition. Additionally, it adds a more toonish quality to characters, and moves away from the 2.5D PVC look, (still capable of that style, but less biased towards it).See full description for added models.

Files with SHA256: 08c87319085355a7150e537a3533cdad17b92e6be39dd502449215ad05e86f0c