CivArchive
    Stillroom - Krea/MOSS/H3 - MOSS 1.0
    NSFW
    Preview 148595686
    Preview 148595687
    Preview 148595688
    Preview 148595689
    Preview 148595690
    Preview 148595744
    Preview 148595745
    Preview 148595746

    Quiet rooms, cold light, a woman alone with the afternoon. Stillroom is Krea 2 Turbo with a style merged into its weights: washed, cold color, low natural light, worn European interiors, the texture of a film photo.

    Write the scene. Stillroom brings the rest.

    Use

    • Put the file in models/diffusion_models and load it with Load Diffusion Model, like the official Krea 2 Turbo. Same text encoder (qwen3vl_4b_fp8_scaled, type krea2) and VAE (qwen_image_vae).

    • 8 to 10 steps, CFG 1, euler, simple.

    • Tested at 1024x1280 (4:5).

    • No trigger word. The style lives in the weights.

    • No need to ask for film, grain, palette or mood. The prompts in the gallery describe the scene and nothing else.

    Files

    • fp8 (13.1 GB): runs on a 16 GB card. Same format as the official krea2_turbo_fp8_scaled from Comfy-Org.

    • bf16 (26.3 GB): full precision, for merging and training on top.

    What to expect

    • Wide city squares drift toward Paris.

    Made from

    Original style. Adults only, in the data and in the gallery.

    License

    Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.

    This model was modified: it is Krea 2 Turbo with a style merged into its weights. It is not an official Krea product and is not endorsed by Krea.

    Reuploading this model, hosting it on another site, or training another model on its outputs needs our permission first. For a commercial license, message us here.

    Description

    The same register on MOSS Image: cold washed color, low natural light, rooms that have been lived in, merged into MOSS-Image SFT.

    • Load it with Load Diffusion Model, like the official MOSS-Image SFT. Text encoder qwen3.5_9b (type moss_image), VAE flux2-vae.
    • 30 steps, CFG 3, euler / simple, SkipLayerGuidance on layer 22 for the first half, as in the official workflow. Tested at 1024x1280.
    • No trigger word. Write the scene; the style lives in the weights.
    • int8 convrot (5.4 GB): same layout as Comfy-Org's moss_image_sft_int8_convrot, runs on a 16 GB card. bf16 (9.7 GB): full precision, for merging and training on top.
    • Next to the Krea 2 version it is sharper and a little cleaner. Peeling walls, worn floors and the cold light come through; the film wash is lighter.
    • Place the camera with words like "seen from behind" or "seen from above". A camera set at a person's distance ("the camera is behind her on the shore") puts a second woman in the frame.

    On .red

    Describe an adult body in plain words: a fit, toned body, a defined waist, full natural breasts. "Toned" can tip into gym abs; drop it if the waist gets hard. Say what is off and what stays: a shirt open at the front, a lace curtain in one hand.

    MOSS-Image is licensed under the Apache License 2.0. This model was modified: a style was merged into MOSS-Image SFT. Every image in the gallery carries its prompt and settings.

    FAQ

    Checkpoint
    MOSS Image

    Details

    Downloads
    324
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/11/2026
    Updated
    11/16/2026
    Deleted
    -

    Files

    stillroom_moss_v1_int8_convrot.safetensors

    stillroom_moss_v1_bf16.safetensors

    Mirrors