CivArchive
    CyberRealistic Anima - v6.0 (Aesthetic V1.1)
    NSFW
    Preview 137085247
    Preview 137080135
    Preview 137080073
    Preview 137085316

    You can get this model through Civitai Early Access, or grab it along with many others by joining The Tinkerer on Whop. Membership gets you early releases, private tools and members-only pages. There are free pages too, no membership needed.

    👉 Join on Whop
    đź’¬ Join the community for support, free tools and early news on Discord

    Download the CyberRealistic Anima ComfUI Workflow here
    It works perfectly in Forge Neo as well.

    CyberRealistic Anima is a full finetune of Anima (CircleStone Labs, built on NVIDIA Cosmos-Predict2-2B with a Qwen3-0.6B text encoder). The base model leans plain, neutral, and anime-first. This finetune pushes the other way, into semi-realistic territory that leans toward realistic: more detailed skin and faces, richer shading, stronger texture, with a polished painterly finish. It keeps Anima's tag and natural-language understanding intact.

    It sits between semi-real and full realism rather than aiming for photographs. The base model's official line is "anime only," but CyberRealistic Anima is looser than that in practice. So CyberRealistic Anima covers anime through semi-real and realistic-leaning output. If you need hard, true-photographic realism, a dedicated SDXL or Z-Image realism checkpoint is the better tool.

    What's different from base Anima

    • Tuned toward a semi-realistic, realistic-leaning, painterly aesthetic out of the box.

    • Better skin, faces, and eye detail, with stronger texture response.

    • You lean less on heavy quality-tag stacking to get a polished result.

    • Keeps Anima's full tag and natural-language understanding.

    How Anima prompting works (worth reading if you're coming from SDXL/Illustrious)

    Anima isn't a CLIP/SDXL model. Its Qwen text encoder reads your whole prompt as natural language, so prompting works differently from Illustrious or Pony:

    • Hybrid works best. Mix Danbooru/Gelbooru tags with a short natural-language description. You can prompt with pure tags like in Illustrious, but hybrid leaves far less room for the model to misread you.

    • Skip very short prompts. They give unstable results. For pure natural language, aim for at least two sentences.

    • Lowercase tags, spaces, no underscores (blue eyes, long hair). Score tags are the only tags that keep underscores.

    • Name a character, then describe their appearance and action. This matters most with multiple characters, or the model gets confused.

    • When a tag differs between Danbooru and Gelbooru, go with the Gelbooru version. The easiest way to find one: search name gelbooru, open the page, copy the tag.

    The style slot

    The last quality/style tag drives the overall style, and it's the one you swap to change the look while everything else stays put:

    • anime for default anime illustration

    • anime screencap for a TV-anime / screencap look

    • realistic / real life for a realistic-leaning render

    • @artist name for a specific artist's style (always with the @)

    Quality tags

    Both base-Anima systems work, in any combination:

    • Human-score: masterpiece, best quality, highres, ...

    • Aesthetic-score: score_9, score_8, ... score_1 (note: score_8, not Pony's score_8_up)

    Practical baseline:

    Positive: masterpiece, best quality, highres, score_7, score_8, realistic
Negative: worst quality, low quality, sketch, score_1, score_2, score_3, censored

    Push to score_7, score_8, score_9 for a more polished finish, or drop to score_6, score_7 for a slightly less polished, more "anime" feel. Always pair the score change with a style-slot tag. The negative prompt rarely needs touching, so leave it stable and just tweak the positive. Use the negative to override stubborn attributes the model won't drop from the positive.

    Tag order

    [quality / meta / year / safety + style slot] [1girl/1boy/etc] [character (from series)] [artist @] [general tags]

    Within each section the order doesn't matter. Pair a character with what they are (1girl) and, when it helps, name the series with "from" (e.g. hyuuga hinata from boruto: naruto next generations). Artists need the @ prefix, or the effect is very weak.

    • Resolution: 768Ă—1024, 832Ă—1216, 1024Ă—1536 (or swaps). Higher resolution means better quality and an easier time for the model. Avoid going much past ~2MP. My favorites are 1024Ă—1536 and 768Ă—1024.

    • Highres Fix: worth using. It improves the image a lot.

    • Standard generation: CFG around 5.5 with 40 to 60 steps for best quality, or CFG 4 to 5.5 with about 28 steps for fast and decent. Don't drop the steps too low (it degrades) or push CFG too high (it burns).

    • Samplers: er_sde (neutral, sharp, a good default), euler_ancestral (softer), dpmpp_2m_sde_gpu (more varied).

    • Scheduler: beta or simple. For the painterly, realistic textures this model is tuned for, try beta57 (ComfyUI RES4LYF node pack). It leans on low-noise timesteps and noticeably improves skin and texture.

    Example prompts

    Realistic-leaning:

    masterpiece, best quality, highres, score_8, score_9, real life, realistic, 1girl, solo. A semi-realistic portrait of a woman with auburn hair and green eyes, natural skin texture, soft window light, shallow depth of field, cinematic.

    Semi-real / painterly with an artist:

    masterpiece, best quality, highres, score_7, score_8, realistic, 1girl, @artist name. A young woman with long silver hair and blue eyes, wearing a white sundress, semi-realistic, detailed skin, soft shading, painterly, depth of field, standing in a sunlit forest with warm cinematic lighting.

    Notes

    • Default to safe and add safety tags (safe, sensitive, nsfw, explicit) to steer content. The model can drift on underspecified prompts.

    • The base Anima checkpoint is a preview still in training, so fine details should keep improving upstream.

    Forge Neo Settings

    You can download the port of RES4LYF Beta57 sigma scheduler from ComfyUI here

    ComfyUI Workflow

    Download the Anima ComfyUI workflow here:
    https://whop.com/joined/cyberdelia-ai-lab/comfy-ui-workflows-anima-7PyhuAgLz9eJ5R/app/

    This is also where future workflow updates will be posted, so make sure to check back for the latest version.

    Credits

    Built on Anima by CircleStone Labs (with Comfy Org), itself a derivative of NVIDIA's Cosmos-Predict2-2B-Text2Image. Please follow the upstream CircleStone Labs Non-Commercial License and the NVIDIA Open Model License where they apply.

    Description

    Grab this model and many more by joining The Tinkerer on Whop. Membership gets you early releases, private tools and members-only pages, plus a lot more.
    👉 Join on Whop

    CyberRealistic Anima V6 is also based on Anima Aesthetic V1.1 and serves as an alternative to CyberRealistic Anima V5. It has a slightly less realistic look, but offers better LoRA compatibility and greater overall flexibility.

    FAQ

    Comments (11)

    goeypants400Jul 18, 2026
    CivitAI

    version 6 released even while version 4 is still in early access

    Cyberdelia
    Author
    Jul 18, 2026

    I understand why it may look strange to see version 6 released while version 4 is still in Early Access.

    The main reason is that I do not develop these models specifically around Civitai’s Early Access schedule. They are primarily created for my Whop subscribers, who get immediate access to all new checkpoints as part of their monthly subscription. Civitai Early Access is simply an additional way for people to support the development and get access before the public release.

    Development also continues while an earlier version is still in Early Access, so newer versions may appear before the previous ones become freely available. I realize that having four checkpoints in Early Access at the same time may be a bit much - but it is what it is.

    For people who want access to all Early Access models, rather than purchasing them separately, the Tinkerer subscription includes every Early Access checkpoint as well as several other tools and benefits.

    TheEventHorizonJul 18, 2026
    CivitAI

    so is aesthetic less realistic than v3?

    Cyberdelia
    Author
    Jul 18, 2026· 1 reaction

    No, did I say that anywhere?

    Just to clarify:

    CyberRealistic Anima V4 → based on Anima Aesthetic V1.0
    CyberRealistic Anima V4.2 → based on Anima Turbo
    CyberRealistic Anima V5 → based on Anima Aesthetic V1.1
    CyberRealistic Anima V6 → based on Anima Aesthetic V1.1

    You can think of CyberRealistic Anima V6 more as an alternative version of V5.

    Each version also includes a comparison between the different versions.

    TheEventHorizonJul 18, 2026· 2 reactions

    @Cyberdelia Sorry, I thought you were going for a more stylized look due to mostly having 2D art examples as opposed to the examples in v3. But thanks for clarifying.

    Cyberdelia
    Author
    Jul 18, 2026· 2 reactions

    @TheEventHorizon Oh, I understand why you thought that. The reason I haven’t included many realistic images with the latest versions is that they’re simply less interesting to showcase. The non-realistic images are harder to create with something like V3, whereas the latest version can handle them much better.

    Cyberdelia
    Author
    Jul 18, 2026· 2 reactions

    @TheEventHorizon V6 is the most flexibele

    SinWhisperJul 19, 2026
    CivitAI

    How much better is v6.0 (Aesthetic V1.1) than v4.0 (Aesthetic V1.0)?

    Cyberdelia
    Author
    Jul 19, 2026· 1 reaction

    No, it’s not necessarily better.. just different. So if you already have V4, there’s no real need to switch to V5.

    V6 is a different story. I do think it’s somewhat “better,” although it’s also less realistic. That said, I don’t think this model should be judged solely by how realistic it is. If realism is your main priority, you’re better off using a different model, such as Z-Image.

    So, if you already have V4, I don’t think you need to switch. But if you don’t have V4 or anything newer yet, try either V5 or V6. My personal recommendation would be V6 (that's what I use).

    SinWhisperJul 19, 2026· 1 reaction

    @Cyberdelia version 4 completely satisfies me, thank you very much for the good work - it is a real pleasure to use your models!

    PlayAIJul 25, 2026
    CivitAI

    can we get this in int8 convrot ?

    Checkpoint
    Anima
    by Cyberdelia
    Download (Beta) View on CivitAI
    art
    base model
    illustration
    realistic
    semi-realistic
    amime

    Details

    Downloads
    1,111
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/18/2026
    Updated
    8/13/2026
    Deleted
    -

    Files

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (220 mirrors)
    CivitAI (166 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (5 mirrors)

    cyberrealisticAnima_v60AestheticV11.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (103 mirrors)
    CivitAI (151 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)

    cyberrealisticAnima_v60AestheticV11.safetensors

    Size:
    3.96 GB
    SHA256:
    bd7f575c441aa07b434f05ae64054f62618570d5283148fa84c9be5ba2632a97

    Mirrors

    CivitAI (1 mirrors)