Ars Goetia is series of loras made on a whim, on variety of images, made from mix of Midjourney, Tumblr, NijiJourney and many more things. Each Demon brings something different. Quality might vary between loras - it's small experiment for me.Trigger words makes lora much stronger.Recommended settings for Anima:<pre><code>Sampler: er_sde | euler | dpmpp_sde_gpu
Scheduler: beta | linear_quadratic | simple
Lora Strength: 0.6-0.8 | Steps: 25 | CFG: 4</code></pre>Recommended settings for Krea2Turbo:<pre><code>Sampler: er_sde | euler
Scheduler: beta | linear_quadratic | simple
Lora Strength: 0.8-1.4 | Steps: 8-10 | CFG: 1</code></pre>Recommended settings for MOSS-Image:<pre><code>Base with 8step turbo lora
Sampler: euler
Scheduler: simple
Lora Strength: 0.8-1.2 | Steps: 8-16 | CFG: 1-3</code></pre>

AG: Astaroth - Vintage Anime

ASTAROTH-KREA-V1.safetensors

Krea2Turbo

MOSS-Image

Anima

Ars Goetia is series of loras made on a whim, on variety of images, made from mix of Midjourney, Tumblr, NijiJourney and many more things. Each Demon brings something different. Quality might vary between loras - it's small experiment for me.Trigger words makes lora much stronger.Recommended settings for Anima:My personal recommendation of checkpoint: <a target="_blank" rel="noopener noreferrer nofollow" href="https://tensorhub.art/models/1007598552668471007">MindShift</a>Sampler:<ul><li>er_sde</li><li>euler</li><li>dpmpp_sde_gpu</li></ul>Scheduler:<ul><li>beta - for more drawn style</li><li>linear_quadratic - for more softened, 3d look</li></ul>Sampling steps: 25-40CFG: 4-5Lora Strength: 0.6-0.8

Files with SHA256: 6ac43ac892d3624269200b5d62478773d37809d4e69c251e7f298eef0c17d0c9