<h3 id="v2-update:">V2 Update:</h3>Please, check on "About this version" for important changes on positive, negative and schedulers.Thank you for using the unmeasurable strength of VALKIRIA ___________________________________________________________________________________ Thanks to FeuerWalkure this model is possible, and that's why it's called... ValkiriaI started finetuning and making PonyMan what she asked, and realized that, at some point, I got two different safetensors... one more anime-aesthetic with 2.5D style and NSFW focused (PonyMan v3) and this one, a fine extra-detailed with more vivid colors and a large range of styles and colors.Valkiria can understand a bit better prompts mixing natural language as well as tag-style. Can do manly bara and feminine girls without mixing them together.I didn't tag a single character on dataset so I WILL struggle to make "popular" character, just use a LoRa.Just try the Valkiria, you won't get disappointed.It origin was Pony (almost forgotten by now) so you could use<pre><code>score_9, score_8_up, score_7_up,</code></pre>for more "anime, pony models aesthetic" outcomes.<pre><code>rating_safe</code></pre>Will guide your picture in case you asked for spicy content but are getting just XXX<pre><code>rating_explicit</code></pre>will do the opposite.<pre><code>NSFW,</code></pre>Not only changes the theme, but also has impact on colors and lights. (client asked this)<pre><code>Real, 3D,</code></pre>Can make things a bit more realistic, but you will need to use lower CFG (0.5 to 1 point lower tha usual, never below 3)Sampler: Euler, DDIM, Euler_ancestalScheduler: Simple, Normal, KarrasSteps: 10 to 22~24 (less: artifacts - more: mutations, usually)CFG: 3 to 7 (only use 7 with more than 20 steps)Negative words:<pre><code>bad quality, worst quality, worst detail, artifacts, signed, censor, (bad hand, bad feet), long chest, chibi, cute themed, jpeg artifacts, lowres, watermark</code></pre>

Valkiria

40% Pony 40% Illustrious and 20% SD 1.5 resources merged along (a lot of crash and retry) I think it's more flexible now. ___READ____ IT WORKS WITH TWO DIFFERENT SETS OF PROMPTS:= - _| Realistic |_ - =Positive: (kinda "safe" by default, but "explicit" forces detailed genitals and poses)<pre><code>(score_9, score_8_up, ultra detailed, high quality, source_anime, rating_ ),</code></pre>Negative: <pre><code>realistic, 3D, low quality, worst quality, jpeg artifacts, fused elements, blurry, bad anatomy, worst detail, censor, lowres, watermark, bad quality, score_6, score_5, logo, artist name, bad hands, patreon, &lt;Capitan_error&gt;</code></pre>|* - _ Anime (many styles) _ - *|Positive: (same thing with "rating" )<pre><code>(score_9, score_8_up, ultra detailed, high quality, real, 3D, rating_ ),</code></pre>Negative:<pre><code>anime, cartoon, low quality, worst quality, jpeg artifacts, fused elements, blurry, bad anatomy, worst detail, censor, lowres, watermark, bad quality, score_6, score_5, logo, artist name, bad hands, patreon, &lt;Capitan_error&gt;</code></pre>- Sampler: Euler_A, DPMpp SDE or DDIM- Scheduler: SGM Uniform, Karras or Normal- 14 ~ 22 steps- 3.7 ~ 5.5 cfg

Files with SHA256: d6d346e98645c74e3b766bd563cab6a33377c5611012b196780986aeb2e13ede