CivArchive
    Lunakrea - v1.0
    NSFW
    Preview 145963555
    Preview 145963563
    Preview 145963567
    Preview 145963570
    Preview 145963572
    Preview 145963573
    Preview 145963575
    Preview 145963576
    Preview 145963578

    🌙 Lunakrea

    Warm light, clean lines, and a soft spot for the moon.

    Lunakrea is a Krea 2 merge that leans toward luminous, storybook anime with a semi-real finish. It takes the bright, warm palette of Krea CinnamonSaphire, folds in the anime detail of VXP Krea2 Beta 4 (Anime), and has the TextFusion Refusal-Reduction LoRA baked straight into its weights. The result follows long, natural-language prompts closely without any extra LoRAs.

    It loves a glowing light source (lanterns, neon, moonlight, oven fire), and it renders quoted text cleanly, so posters, shop signs and chalkboards are fair game.

    No trigger words. Just describe the scene.

    🌒 The recipe

    1. Base (A): Krea CinnamonSaphire v2.0 by Doughboy645
    2. Blended in (B): VXP Krea2 Beta 4 (Anime) by VXP, via mikmod's INT8 release, with SLERP at t = 0.35 (roughly 65 % A / 35 % B)
    3. Baked in: Krea2 TextFusion Refusal-Reduction LoRA v2.0 Full Rank by Capitan01R, at strength 1.0

    SLERP blends along the arc between the two models instead of averaging in a straight line, so neither parent washes the other out. The LoRA only touches Krea 2's text-fusion layers: the look comes entirely from the merge, while the LoRA changes how the prompt is read. Merged, baked and converted locally with stable-diffusion.cpp.

    🌓 Settings

    • Steps: 10 (8–12 works)
    • CFG: 1. It is a turbo-style model, so negative prompts have no effect at CFG 1.
    • Sampler / scheduler: ER SDE + simple
    • Resolution: 832×1216 portrait, 1216×832 landscape
    • Text encoder: the Krea 2 Qwen3-VL 4B encoder (the showcase used Ektome-Qwen3-VL-4Bi-PristinelyUncensored Q4_K_M)
    • VAE: qwen_image_vae.safetensors

    The text encoder and VAE are not part of this upload. Use the ones you already have for Krea 2.

    🌔 Prompting

    Write it the way you would describe a painting to a friend: the subject first, then what they are doing, where they are, how the scene is lit, and finally the style.

    • Full sentences beat tag lists. Weight syntax like (word:1.2) is read as literal text.
    • Put any text you want in the picture in double quotes and say where it goes: a chalkboard on the wall reads "LUNA BAKERY".
    • Lunakrea defaults to warm and bright. If you want dark and gritty, ask for it explicitly.

    🌕 Which file?

    • BF16 · lunakrea-v1-bf16.safetensors · 25.6 GB: the full-precision master, for merging, training or making your own quants.
    • FP8 (scaled) · lunakrea-v1-fp8_scaled.safetensors · 13.5 GB: a lighter safetensors file for ComfyUI.
    • Q8_0 · lunakrea-q8_0.gguf · 13.6 GB: near-lossless GGUF. Every showcase image was rendered with this exact file.
    • Q5_K · lunakrea-v1-q5_K.gguf · 8.8 GB: for tighter VRAM, at a small quality cost.
    • Q4_K · lunakrea-v1-q4_K.gguf · 7.2 GB: the smallest file; some fine detail is lost.
    • INT8 · lunakrea-v1-int8.safetensors · 13.5 GB: for ComfyUI INT8 (convrot) workflows. It also runs natively in recent stable-diffusion.cpp builds.
    • W4A4 · lunakrea-v1-int4_convrot.safetensors · 9.4 GB: ComfyUI INT4 W4A4. Experimental, and it does not run in stable-diffusion.cpp yet.

    The other formats are 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 and the refusal-reduction LoRA is baked in, so Lunakrea handles mature content when you prompt for it. 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

    A young woman with long silver hair and pale violet eyes stands on the tiled rooftop of an old Japanese inn at night, holding a glowing paper lantern in one hand. She wears an indigo kimono patterned with small white crescent moons and a loose obi that flutters in the wind. Behind her an enormous full moon fills half the sky, soft clouds drifting across it, and the warm orange lantern light mixes with the cool blue moonlight on her face. Full-body shot from a slightly low angle, detailed anime illustration with soft painterly shading and fine linework.

    10 steps · CFG 1 · ER SDE / simple · 832×1216 · seed 7110422

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

    🌘 Credits

    Thank you to Doughboy645 (CinnamonSaphire), VXP (VXP Krea2) and mikmod (its INT8 release), Capitan01R (TextFusion Refusal-Reduction), and the Krea team for Krea 2. Lunakrea would not exist without their work. 💜

    Description

    v1.0: first light 🌙

    • SLERP merge of Krea CinnamonSaphire v2.0 (A) and VXP Krea2 Beta 4 Anime (B), t = 0.35
    • Krea2 TextFusion Refusal-Reduction LoRA v2.0 Full Rank baked in at 1.0
    • Seven formats: BF16, FP8 (scaled), Q8_0, Q5_K, Q4_K, INT8 and W4A4
    • Recommended: 10 steps · CFG 1 · ER SDE / simple · 832×1216

    FAQ

    Comments (2)

    mikmodOct 19, 2026· 2 reactions
    CivitAI

    This DiT look very promising, which UI does support it? Because ComfyUI, at least on v0.38, doesn't seem to want to even load it. I've tested int8, fp8 and bf16 variants.

    If I try to load any of the mentioned variants, I'll get tuple index out of range error. :)

    killerrr2008380Oct 19, 2026

    int4 too (((((

    Checkpoint
    Krea 2
    by raezor07
    Download (Beta) View on CivitAI
    krea2
    krea 2
    anime
    semi-realistic
    illustration
    merge
    gguf
    base model

    Details

    Downloads
    109
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/17/2026
    Updated
    10/19/2026
    Deleted
    -

    Files

    lunakrea_v10_q4KS.gguf

    Size:
    6.72 GB
    SHA256:
    e036e54e48b21b4268df0d92c210e03b7c0aaa19b495d549ea7e68b6c0660341

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_bf16.safetensors

    Size:
    23.88 GB
    SHA256:
    096a2f29f4e3ccdd430e2084bab54e771d6288cb3c57b597faed40815e8efd6f

    Mirrors

    CivitAI (1 mirrors)

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (329 mirrors)
    CivitAI (281 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (6 mirrors)

    lunakrea_v10_fp8Scaled.safetensors

    Size:
    12.56 GB
    SHA256:
    6614eb3fc1478046451696b6f8e7362e7cc3d6d6bee989b1cbbe43fa60d98737

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_q80.gguf

    Size:
    12.69 GB
    SHA256:
    1bcfd1b17211b5198655a7335386d2b6e0cdcf57b3aa36c2b75db00ccc1c286a

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_int4.safetensors

    Size:
    8.71 GB
    SHA256:
    e9f166047201689c223ffc057e649b1e322884ad68b0e07936b8832fe318c407

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_int8.safetensors

    Size:
    12.57 GB
    SHA256:
    88a46810f1083bd111919013ed48bafc0d7eda9e271d494f0df9099681cd2496

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_txt.gguf

    Size:
    2.33 GB
    SHA256:
    c032adc3badb2b72db7c31b5bbeda39ef7c2b6991e5a50e30a4528fe843cf0f8

    Mirrors

    CivitAI (1 mirrors)

    lunakrea_v10_q5KS.gguf

    Size:
    8.21 GB
    SHA256:
    280bbbd3c2b8a7db1aed27dd7e4b464985ce1b831bc23f4294a28d6b2c80dc03

    Mirrors

    CivitAI (1 mirrors)