<h1 id="v4.3-final">v4.3 [final]</h1>I recommend to choose this one or v2. If you don't care about speed and want great anime results use this model + LCM sampler + 20 steps. It's simply better than any model I know in this aspect.<h3 id="recommended-settings:">Recommended settings:</h3>6+ steps (8 + 4 steps of upscaler is optimal for my use cases, feel free to experiment).A few options of samplers:<ul><li>CFG 1.8 | Euler A</li><li>CFG 2.0 | LCM - better for anime and other abstract things.</li><li>CFG 1.8 | DPM++ 2M SDE with BETA scheduler (normal doesn't work)</li></ul>Use style tags such as "anime style, flat coloring" or artist/title name. It will help model to know what you want from it.The fastest generation: use CFG 1.0 and set lora CFG_slider on negative -0.4 value. Lora listed in suggested resources. (CFG 1.0 ignores negative prompt. Don't use it if you need negative)The best coherency: use CFG 2.8 and CFG_slider lora on +0.75 weight (for Euler A).<h1 id="v3.2b">v3.2B</h1>Recommended settings:<ul><li>CFG 1.8</li><li>LCM / [kl optimal / sgm uniform]</li><li>5-10 steps</li></ul><h1 id="v3.2a">v3.2A</h1>Recommended settings:<ul><li>CFG 1.8 (works not bad on cfg 1 as well)</li><li>Euler A / normal</li><li>5-10 steps</li></ul><h1 id="v1.99-(v-prediction)">v1.99 (v-prediction)</h1>Use title or artist name to get a specific style.Eauler A - Beta scheduler (or normal)8-16 stepsCFG: 1.0 recommended for 2x speed. Use more if you want to use negative prompt.<h1 id="v2">v2</h1>Sampler: Euler A / Euler A cfg++CFG: (depends on sampler)Alternative sampler: LCM

ALF mix (IL, 8 steps generation)

alfMixIL8Steps_v10.safetensors

ALF mix (IL, 12 steps generation)

v1.0

v4.3 [final]

v4.1 [experimental]

v4.0 (clear)

v3.2B

v3.2a

v.1.99 (v-prediction)

v2.0 (monster)

It's just a mix of a few models and specific weights of LCM lora. This checkpoint will help you if you want to generate images faster by price of some details quality.You can get better results by using ModelSamplingDiscrete with selected "lcm" option in ComfyUI.2.1 - CFG for EulerA cfg++ sampler (not recomended without ModelSamplingDiscrete)3.0+- - default CFG for LCM sampler. It depends on your prompt. You should to increase it, if your results have dull colors.You can generate good results even with 9 steps in some cases.Use example images as workflows if you have ComfyUI. There are some difference in settings among examples. You can try to use other samplers - I haven't tested them all, so something else can work better.I haven't tested it for 15+ steps. You can try, if you are curious. Maybe it's not so bad with default generations.

alfMixIL12Steps_v10.safetensors

Files with SHA256: ea839b5ad79debe24a30950674491d14b270b5f4c962591fe6a17985bc57df3c