CivArchive
    LunaKrea - v2.0
    NSFW
    Preview 148630139
    Preview 148630140
    Preview 148630141
    Preview 148630144
    Preview 148630147
    Preview 148630152
    Preview 148630153
    Preview 148630156
    Preview 148630157
    Preview 148630164
    Preview 148630168
    Preview 148630171
    Preview 148630173
    Preview 148630176
    Preview 148630179
    Preview 148630181
    Preview 148630184
    Preview 148630185
    Preview 148630189
    Preview 148630191

    ๐ŸŒ™ LunaKrea

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

    Lunakrea is a Krea 2 merge that leans toward luminous, storybook illustration with a semi-real finish. v2.0 keeps what made v1 work, the bright, warm palette, the clean anime detail and the baked-in TextFusion Refusal-Reduction LoRA, and blends in MoonMaster Narrative Drift, a Krea 2 Turbo checkpoint built to paint rather than photograph. The result leans further into digital painting: richer colour, stronger shapes, deeper shadows and more expressive light. It 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.

    ๐ŸŒ’ The recipe

    v2.0

    1. Base (A): LunaKrea v1 at full precision (v1.0 and v1.1 share the same weights)
    2. Blended in (B): ๐Ÿป MoonMaster Narrative Drift v1.0 by Moonbear_AIArt, with SLERP at t = 0.35 (roughly 65 % A / 35 % B)

    LunaKrea v1, the A side:

    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
    3. Baked in: Krea2 TextFusion Refusal-Reduction LoRA v2.0 Full Rank by Capitan01R, at strength 1.0

    SLERP blends along the arc between two models instead of averaging in a straight line, so neither parent washes the other out. The refusal-reduction LoRA rides along inside LunaKrea v1, so in v2.0 the blend dilutes it to roughly two-thirds of its strength; the look comes from the merges, while the LoRA changes how the prompt is read. Merged and converted locally with SevenHarness and stable-diffusion.cpp.

    ๐ŸŒ“ Settings

    • Steps: 10 (8โ€“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: 832ร—1216 portrait, 1216ร—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 attached as optional components. Skip them if you already have Krea 2's.

    ๐ŸŒ” 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.

    ๐ŸŒ• Which file?

    • BF16 ยท lunakrea-v2.0-bf16.safetensors ยท 25.6 GB: the full-precision master, for merging, training or making your own quants.
    • FP8 (scaled) ยท lunakrea-v2.0-fp8_scaled.safetensors ยท 13.5 GB: a lighter safetensors file for ComfyUI.
    • Q8_0 ยท lunakrea-v2.0-q8_0.gguf ยท 13.6 GB: near-lossless GGUF. Every v2.0 showcase image was rendered with this exact file.
    • Q5_K ยท lunakrea-v2.0-q5_K.gguf ยท 8.8 GB: for tighter VRAM, at a small quality cost.
    • Q4_K ยท lunakrea-v2.0-q4_K.gguf ยท 7.2 GB: the smallest file; some fine detail is lost.
    • INT8 ยท lunakrea-v2.0-int8.safetensors ยท 13.5 GB: for ComfyUI INT8 (convrot) workflows. It also runs natively in recent stable-diffusion.cpp builds.
    • W4A4 ยท lunakrea-v2.0-int4_convrot.safetensors ยท 9.4 GB: ComfyUI INT4 W4A4. Experimental, and it does not run in stable-diffusion.cpp yet.

    Every format is converted directly from the BF16 master, never from another quant, with the same ComfyUI-safe converter as v1.1. GGUF files need ComfyUI-GGUF with Krea 2 support (such as molbal/ComfyUI-GGUF), Forge or stable-diffusion.cpp.

    ๐ŸŒ– Versions

    • v2.0: LunaKrea v1 blended with MoonMaster Narrative Drift. More painterly, same warmth.
    • v1.1: the v1.0 weights, with every file rebuilt so it loads in ComfyUI.
    • v1.0 (broken): the first release. Its files stop in ComfyUI with "tuple index out of range"; use v1.1 or v2.0 instead.

    ๐ŸŒ— Content note

    LunaKrea's v1 parents are NSFW-capable and the refusal-reduction LoRA rides along, so LunaKrea handles mature content when you prompt for it. One v2.0 showcase image (the hot spring) contains nudity; everything else is SFW. All characters are adults. Please follow CivitAI's rules and the laws where you live.

    โš–๏ธ Permissions

    v2.0 contains MoonMaster Narrative Drift, whose license asks that shared merges keep its permissions: generate with LunaKrea locally, on hardware you control, or on CivitAI, but please do not host it on third-party generation platforms such as TensorArt or SeaArt. Credit the creators when you share a merge of it.

    ๐ŸŒ˜ 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 ยท CFG 1 ยท ER SDE / simple ยท 832ร—1216 ยท seed 1818456205

    Every showcase image keeps its full prompt and settings, so you can remix any of them. The v2.0 showcase reuses the v1.1 prompts on the same seeds (one prompt is replaced by a new LunaKrea poster), so you can compare the two versions image by image.

    ๐Ÿ’œ Credits

    Thank you to Moonbear_AIArt (MoonMaster Narrative Drift), 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. ๐Ÿ’œ

    Description

    v2.0: Narrative Drift ๐ŸŒ™

    • A new blend: LunaKrea v1 (A) SLERP-merged with ๐Ÿป MoonMaster Narrative Drift v1.0 by Moonbear_AIArt (B), t = 0.35, roughly 65 % LunaKrea / 35 % MoonMaster
    • What changes: MoonMaster is a Krea 2 Turbo checkpoint built to paint rather than photograph. LunaKrea keeps its warm, luminous palette and clean anime lines, and picks up richer colour, stronger shapes, deeper shadows and more expressive light
    • The TextFusion Refusal-Reduction LoRA comes along inside LunaKrea v1, diluted by the blend to roughly two-thirds of its strength
    • Seven formats, all converted from the BF16 master: BF16, FP8 (scaled), Q8_0, Q5_K, Q4_K, INT8 and W4A4 (INT4 convrot). They load in ComfyUI and stable-diffusion.cpp; GGUFs in ComfyUI need a ComfyUI-GGUF build that knows Krea 2, such as molbal/ComfyUI-GGUF
    • Optional components: the Qwen3-VL 4B text encoder (Q4_K_M) and the Qwen Image VAE
    • Showcase: the v1.1 prompts on the same seeds, so you can compare the versions image by image (one prompt replaced by a new LunaKrea poster), all rendered with the Q8_0 file
    • Permissions: MoonMaster's terms apply. Generate locally, on hardware you control or on CivitAI, not on third-party generation platforms
    • Recommended: 10 steps ยท CFG 1 ยท ER SDE / simple ยท 832ร—1216

    FAQ

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

    Details

    Downloads
    78
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/11/2026
    Updated
    11/12/2026
    Deleted
    -

    Files

    lunakrea-v2.0-fp8_scaled.safetensors

    Size:
    12.56 GB
    SHA256:
    96ab8152a90da7eaa10b9e3e7ac283fe2e93cb1712606ee7ffc013a86fd24f04

    Mirrors

    CivitAI (1 mirrors)

    lunakrea-v2.0-bf16.safetensors

    Size:
    23.88 GB
    SHA256:
    bde258daa0bbc26282055a27734d965fe964c6fe9e63ebf578057c9337d29fad

    Mirrors

    CivitAI (1 mirrors)

    lunakrea-v2.0-q4_K.gguf

    Size:
    6.72 GB
    SHA256:
    8bef8632f38c733a628e8faf244588995e75c30415b00524b3cb66dea4100e9a

    Mirrors

    CivitAI (1 mirrors)

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (363 mirrors)
    CivitAI (310 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (7 mirrors)

    Ektome-Qwen3-VL-4Bi-PristinelyUncensored.Q4_K_M.gguf

    Size:
    2.33 GB
    SHA256:
    c032adc3badb2b72db7c31b5bbeda39ef7c2b6991e5a50e30a4528fe843cf0f8

    Mirrors

    CivitAI (4 mirrors)

    lunakrea-v2.0-q5_K.gguf

    Size:
    8.21 GB
    SHA256:
    55d76414a4112fbfd4770bc66431e96059933119880b5079961bf2ec089778f9

    Mirrors

    CivitAI (1 mirrors)

    lunakrea-v2.0-int8.safetensors

    Size:
    12.57 GB
    SHA256:
    095f11a9b401787be28c3fb07d0d11e021a55f4f7014c43a67fa6059923c533d

    Mirrors

    CivitAI (1 mirrors)

    lunakrea-v2.0-q8_0.gguf

    Size:
    12.69 GB
    SHA256:
    34d5485ae56a90ed935a9afca705834684d9f3f28cef79feff7a15bf3656e2bb

    Mirrors

    CivitAI (1 mirrors)

    lunakrea-v2.0-int4_convrot.safetensors

    Size:
    8.71 GB
    SHA256:
    8a4085925e8e00e6a4dcc91b25b937db0d62344f5bc27692640505f39a4ce71d

    Mirrors

    CivitAI (1 mirrors)