My most popular Lora in Illustrious, created a Version for Anima. Ideal for Anime art, character design, and vibrant illustrations.
This LoRA model blends vibrant, multicoloured shading techniques with sketches.
Requirements:
or
Recommended Settings
Display Resolutions:
1024 × 1024
1254 × 836
1365 × 768
Sampling:
CFG Scale: 3 – 6
Steps: 20 – 30
Samplers: Euler A Normal / ER SDE BETA / ER SDE SIMPLE
Quality Tags
Human Score–Based:masterpiece, best quality, good quality, normal quality, low quality, worst quality
PonyV7 Aesthetic Model–Based:score_9, score_8, score_7, score_6, score_5, score_4, score_3, score_2, score_1
Negative Prompt
worst quality, low quality, score_1, score_2, score_3, artist name, (lowres:1.2), (worst quality:1.4), (low quality:1.4), (bad anatomy:1.4), bad hands, multiple views, comic, jpeg artifacts, patreon logo, patreon username, web address, signature, watermark, text, logo, artist name, censored, mosaic censoring
Meta Tags
highres, absurdres, anime screenshot, jpeg artifacts, official art, etc.
Safety Tags
safe, sensitive, nsfw, explicit
Description
FAQ
Comments (4)
这个lora非常神奇的在强化镜头感和人物动态方面有很好的效果，至于画风方面的影响反而不是太大
Can confirm this lora introduces some genuinely interesting compositions, especially with dynamic angles, it also produces deeper and sharper shadows. That said, it also desaturates the palette noticeably and tends to place character faces in shadow even with negative prompting, which is a bit of a tradeoff. Still, the overall effect is fascinating, it really keeps images from feeling flat or generic.
Appreciate the feedback, I'll keep that in mind while working on the updated version . Does the face shadow also happen at CFG 5–7 even with negative prompting?
I've tested it across CFG 3 to 6, and I honestly couldn't find a negative prompt that consistently counters the face shadowing. Most of my results end up with lighting similar to your example images 2, 3, and 4 on this page, where the face specifically falls into shadow while the rest of the scene is lit, which does look a bit off.
I've also noticed the LoRA doesn't actually affect the art style much, it gets completely overwritten by other style LoRAs, but its impact on composition and camera angles is genuinely interesting, it keeps Anima from defaulting to the same stale compositions when you give it detailed prompts. I've been using it mainly as a composition enhancer at 0.7 strength.
Really appreciate the work you put into this, thanks for sharing it.