CivArchive
    SolAnima - v1.0
    NSFW
    Preview 146562344
    Preview 146562346
    Preview 146562348
    Preview 146562352
    Preview 146562356
    Preview 146562359
    Preview 146562361
    Preview 146562362
    Preview 146562363
    Preview 146562366
    Preview 146562370
    Preview 146562371
    Preview 146562376
    Preview 146562377
    Preview 146562381
    Preview 146562387
    Preview 146562392
    Preview 146562395
    Preview 146562400
    Preview 146562403

    ☀️ SolAnima

    Golden light, bold colour, and skies that glow.

    SolAnima is an Anima merge built for bright, saturated, sun-soaked anime: crisp cel shading, glossy highlights and luminous skies. It blends the versatile Ghostbubblehybrid V3 with the neon-bright, glossy colour of Berry Model Raspberry v5.0, evenly, with nothing else baked in.

    It loves sunrise, high noon and golden hour, and short text in quotes renders well, so posters and signs are fair game.

    No trigger words. Use Anima's usual quality tags and describe the scene.

    🌄 The recipe

    1. Base (A): Ghostbubblehybrid V3 by sbbell8295
    2. Blended in (B): Berry Model Raspberry v5.0 by irregular_degular, with SLERP at t = 0.5 (an even 50 / 50)

    Raspberry v5.0 is itself a blend of mommymia's Marshmallow Milk Anima and Dessert Models Anima (Chocolate Fudge), according to its file metadata, so their style runs through SolAnima too.

    SLERP blends along the arc between the two models instead of averaging in a straight line, so neither parent washes the other out. No LoRAs were added. Merged and converted locally with stable-diffusion.cpp.

    ☀️ Settings

    • Steps: 30
    • CFG: 4. Anything from 1.5 to 5 works: lower is softer and faster, higher is punchier and follows the prompt more closely.
    • Sampler / scheduler: Euler a + simple
    • Resolution: 832×1216 portrait, 1216×832 landscape
    • Negative prompt: worst quality, low quality, score_1, score_2, score_3, artist name, signature, watermark, blurry, jpeg artifacts, chromatic aberration, bad anatomy, bad hands, extra fingers
    • Text encoder: qwen_3_06b_base.safetensors (Anima's Qwen3 0.6B)
    • VAE: qwen_image_vae.safetensors

    The text encoder and VAE are attached to this version as optional downloads, in case you do not have them yet.

    🌤️ Prompting

    Anima understands Danbooru-style tags and natural language, and SolAnima likes both together:

    • Start with masterpiece, best quality, score_7, safe (or nsfw), then 1girl / 1boy / no humans, then tags for the subject, outfit and setting.
    • Follow the tags with two or more full sentences describing the scene, the light and the style. Very short prompts give unpredictable results.
    • Tags are lowercase with spaces instead of underscores. Artist tags need an @ in front.
    • Put text you want in the picture in double quotes: lettering across the top reads "SOLAR EXPRESS". Short, common words come out cleanly; long or unusual words can be misspelled.
    • SolAnima defaults to vivid and sunny. If you want muted or moody, ask for it.

    🌞 Which file?

    • BF16 · solanima-v1.0-bf16.safetensors · 4.2 GB: the full-precision master. Every showcase image was rendered with this file.
    • FP8 (scaled) · solanima-v1.0-fp8_scaled.safetensors · 2.3 GB: a lighter safetensors file for ComfyUI.
    • Q8_0 · solanima-v1.0-q8_0.gguf · 2.2 GB: near-lossless GGUF.
    • Q5_K · solanima-v1.0-q5_K.gguf · 1.5 GB: for tighter VRAM, at a small quality cost.
    • Q4_K · solanima-v1.0-q4_K.gguf · 1.2 GB: the smallest file; some fine detail is lost.
    • INT8 · solanima-v1.0-int8.safetensors · 2.3 GB: for ComfyUI INT8 (convrot) workflows. It also runs natively in recent stable-diffusion.cpp builds.
    • W4A4 · solanima-v1.0-int4_convrot.safetensors · 1.8 GB: ComfyUI INT4 W4A4. Experimental, and it does not run in stable-diffusion.cpp yet.

    Every file is converted directly from the BF16 master, never from another quant. GGUF files need ComfyUI-GGUF, Forge or stable-diffusion.cpp.

    🌇 Content note

    Both parent models are NSFW-capable, so SolAnima handles mature content when you prompt for it with nsfw. The last showcase image contains nudity; everything else is SFW. All characters are adults. Please follow CivitAI's rules and the laws where you live.

    🌆 Cover prompt

    masterpiece, best quality, score_7, safe, 1girl, solo, adult, long hair, golden hair, amber eyes, orange kimono, sun print, obi, holding umbrella, oil-paper umbrella, rooftop, tiled roof, east asian architecture, sunrise, cloud, wind, floating hair, full body, from below. A young woman in her twenties with long golden hair and warm amber eyes stands on the tiled rooftop of an old Japanese inn at sunrise, holding an open red paper parasol over her shoulder. She wears an orange kimono patterned with small golden suns, and her loose obi ripples in the morning breeze. Behind her an enormous rising sun fills half the sky, painting the clouds pink and gold, and soft warm light rims her hair.

    30 steps · CFG 4 · Euler a / simple · 832×1216 · seed 1170421

    Every showcase image keeps its full prompt and settings, so you can remix any of them.

    🌃 Credits

    Thank you to sbbell8295 (Ghostbubblehybrid), irregular_degular (Berry Model), mommymia (Marshmallow Milk and Dessert Models), and Circlestone Labs for Anima. SolAnima would not exist without their work. 🧡

    Description

    v1.0: sunrise ☀️

    • SLERP merge of Ghostbubblehybrid V3 (A) and Berry Model Raspberry v5.0 (B), t = 0.5
    • No LoRAs baked in
    • Seven formats: BF16, FP8 (scaled), Q8_0, Q5_K, Q4_K, INT8 and W4A4 (INT4 convrot), all converted from the BF16 master
    • The text encoder (Qwen3 0.6B) and VAE are attached as optional components
    • Recommended: 30 steps · CFG 4 · Euler a / simple · 832×1216
    Checkpoint
    Anima
    by raezor07
    Download (Beta) View on CivitAI
    anima
    base model
    gguf
    vibrant
    colorful
    illustration
    merge
    anime

    Details

    Downloads
    83
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/23/2026
    Updated
    10/25/2026
    Deleted
    -

    Files

    solanima_v10_q5KS.gguf

    Size:
    1.36 GB
    SHA256:
    b51223cc9bf375a35de5b7bf6d0802ef145e7b5d1e0a97e465352d467da21228

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_q4KS.gguf

    Size:
    1.12 GB
    SHA256:
    b767fbbd441b808bcaa28b1389795f7e8484391c20e847757c4f5fefa258d296

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_txt.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (143 mirrors)
    CivitAI (263 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)

    solanima_v10_bf16.safetensors

    Size:
    3.90 GB
    SHA256:
    d415910e32f9e4931d002ac6a137c4eb89f395dbddc80708f13f03ec21174869

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_int8.safetensors

    Size:
    2.16 GB
    SHA256:
    dba4e583fc4a1462a2907721e070939899a22a251dc95a8af5e450cbbd58b2ae

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_int4.safetensors

    Size:
    1.63 GB
    SHA256:
    2461237eb1f9aebbba8b1680b8c37aeae9a9c6ec31b9d2e4b5167afab89f8a88

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_fp8Scaled.safetensors

    Size:
    2.16 GB
    SHA256:
    4e8d3c09a748ae4a82037babea348823acac57ee628991bb3ef340a2ff55e8ae

    Mirrors

    CivitAI (1 mirrors)

    solanima_v10_q80.gguf

    Size:
    2.09 GB
    SHA256:
    c0cd6de089f74db857a4969784c288d342475ecb78f783becd5d52ed69977a96

    Mirrors

    CivitAI (1 mirrors)

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (339 mirrors)
    CivitAI (289 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (6 mirrors)