Valkyrie Blend offers a 2D anime style, while producing good results even with shorts prompt that only contain 1 or 2 short sentences. Or with only a few tags, when using Booru-Style prompting.

Short and simple prompts work best for SFW concepts. For NSFW, a bit more description of the scene is necessary in order to get good results.

Recommended Settings:

• Sampler / Scheduler: Euler A or ER SDE with Simple or Beta

• Sampling steps: 20-35

• CFG Scale: 3-6

• Shift: 3-4.5

• Recommended resolution: 1024px based or 1280px based

• Model tested with Forge Neo

• VAE and Text Encoder are already merged into the model

Please refer to the official model page for detailed instructions: https://civarchive.com/models/2458426/anima-official

For all samples, the Forge Neo Add-on "Anima Detail Enhancer" was used to improve minor details. Below settings were applied.

I recommend using a post processing upscale instead of a usual High-res fix.

The preview images were 4x upscaled with 4x-ClearRealityV1_Soft.

Quality tags:

Positive:

masterpiece, best quality, score_9

Negative:

score_1, score_2, score_3, blurry, jpeg artifacts,lowres, worst quality, low quality, bad hands, bad anatomy,signature, text, watermark, censor, bar censor, mosaic censorship, mosaic censor, sound effects, blubble speech, patreon logo, patreon username, twitter username, twitter logo, blur, multiple views or similars.

Merged models:

https://huggingface.co/Anzhc/AAAAnima

https://civarchive.com/models/2515015/hakushi-mix-anima?modelVersionId=3001028

and Styling Loras

Permission: no commercial use, no selling, use only on Civitai (please also check the sources for their respective permissions)