anima v2 the animazingXL version of anima. Expect the same quality and fun as the sdxl checkpoint.

all samples are as is, no loras, no detailers, no fixes, just the prompt and the checkpoint : )

check below for about 100 samples : )

no cherry picking - all samples posted where genned one after the other, this model nails the concept fast : ) of course I skip one or two here and there, but for the most part, I got this checkpoint dialed in pretty good : ) this is why i don't release a ton of updates. I take the time to make sure this is a top notch, excellent model, this is how I operate : ) for all my models !!!

Gallery images were created with civitai prompts, a million thanks, I dont have time to write 100 prompts, I mix some with nodes, keep them as you wrote them, my main goal is to show you how diverse the model is, it can handle whatever you throw at it. I test my models for hours before moving forward to publish. I make sure it is the best I can deliver with the time I have. : )

If your new to anima check out:: https://animadex.net

info from https://civarchive.com/models/2458426/anima

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Generation settings

• Works at resolutions between 512^2 and 1536^2 pixels.

• 30-50 steps, CFG 4-6.

• A variety of samplers work. Some of my favorites:

  • er_sde: neutral style, flat colors, sharp lines. I use this as a reasonable default.

  • euler_a: Softer, thinner lines. Can sometimes tend towards a 2.5D look. CFG can be pushed a bit higher than other samplers without burning the image.

  • dpmpp_2m_sde_gpu: similar in style to er_sde but can produce more variety and be more "creative". Depending on the prompt it can get too wild sometimes.

• If going for a more realistic / painterly look, the beta57 scheduler (ComfyUI RES4LYF custom node pack) can help make better textures, since it puts more emphasis on low-noise timesteps.

Prompting

The model is trained on Danbooru-style tags, natural language captions, and combinations of tags and captions.

• Use lowercase for tags, and spaces instead of underscores. Score tags are the only tags that use underscores.

• Recommended positive prefix: "masterpiece, best quality, score_7, safe, "

• Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name"

• When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.

• Prompt weighting works, but needs a weight higher than typically used for SDXL. Example: "(chibi:2)"

Tag order

[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]

Within each tag section, the tags can be in arbitrary order.

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_1

You can use either the human score quality tags, the aesthetic model tags, both together, or neither. All combinations work.

Time period tags

Specific year: year 2025, year 2024, ...

Period: newest, recent, mid, early, old

Meta tags

highres, absurdres, anime screenshot, jpeg artifacts, official art, etc

Safety tags

safe, sensitive, nsfw, explicit

Artist tags

Prefix artist with @. E.g. "@big chungus". You must put @ in front of the artist. The effect will be very weak if you don't.

Full tag example

year 2025, newest, normal quality, score_5, highres, safe, 1girl, oomuro sakurako, yuru yuri, @nnn yryr, smile, brown hair, hat, solo, fur-trimmed gloves, open mouth, long hair, gift box, fang, skirt, red gloves, blunt bangs, gloves, one eye closed, shirt, brown eyes, santa costume, red hat, skin fang, twitter username, white background, holding bag, fur trim, simple background, brown skirt, bag, gift bag, looking at viewer, santa hat, ;d, red shirt, box, gift, fur-trimmed headwear, holding, red capelet, holding box, capelet

Tag dropout

The model was trained with random tag dropout. You don't need to include every single relevant tag for the image.

Dataset tags

To improve style and content diversity, the model was additionally trained on two non-anime datasets: LAION-POP (specifically the ye-pop version) and DeviantArt. Both were filtered to exclude photos. Because these datasets are qualitatively different from anime datasets, captions from them have been labeled with a "dataset tag". This occurs at the very beginning of a prompt followed by a newline. Optionally, the second line can contain either the image alt-text (ye-pop) or the title of the work (DeviantArt). Examples:

ye-pop
For Sale: Others by Arun Prem
Abstract, oil painting of three faceless, blue-skinned figures. Left: white, draped figure; center: yellow-shirted, dark-haired figure; right: red-veiled, dark-haired figure carrying another. Bold, textured colors, minimalist style.

deviantart
Flame
Digital painting of a fiery dragon with glowing yellow eyes, black horns, and a long, sinuous tail, perched on a glowing, molten rock formation. The background is a gradient of dark purple to orange.

@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@

-- info for sdxl model below --

check my profile, i do daily challenges everyday, this will be my new daily driver : )

what's that mean? it rocks !!! and its got an anime flavor to it...

this model have the full range of sdxl models, cartoon, realistic, semi real, etc..., i just made sure it rocked when it came to anime, I love anime and been wanting to have a model that held the anime flavor when loras got added and this does that well : )

capable of nsfw : )