Skip to content
Images

Juggernaut Moss

фотореалистичный файнтюн MOSS-Image

3 min read

Полный файнтюн (дообучение всей модели целиком, а не через LoRA) модели MOSS-Image Base от KandooAI — создателя популярной линейки Juggernaut. Модель заточена под реалистичную фотографию и кинематографичные кадры с естественной текстурой кожи, правдоподобным светом и плёночной атмосферой, при этом сохраняя поддержку других стилей и 18+ контента. В слепых сравнениях с базовой MOSS-Image Base при одинаковых параметрах версия Juggernaut Moss победила в 73 % случаев (или 80 % без учёта ничьих), особенно обогнав оригинал в портретах и кинокадрах. Подойдёт для генерации крупных портретов, атмосферных сцен и работы в ComfyUI в высоком разрешении.

Ключевые особенности

  • Понимание естественного языка: обучена на коротких, средних и длинных текстовых описаниях — лучше всего реагирует на связные предложения с описанием света и камеры, а не на набор тегов через запятую.
  • Две версии весов на выбор: полная BF16 (~10 ГБ) и облегчённая квантованная int8 ConvRot (~5.4 ГБ), которая работает быстрее на большинстве видеокарт и запускается в ComfyUI без кастомных нод.
  • Оптимизация под высокое разрешение: наилучшую детализацию модель выдаёт в диапазоне 1.5K–2K (около 2 мегапикселей, например 1344×1792 или 1536×1536), тогда как на 1024×1024 качество заметно ниже.
  • Свободная лицензия Apache 2.0: разрешает коммерческое использование сгенерированных изображений, слияние весов (merge) и дальнейшее дообучение.

Что можно сделать

  • Крупные портреты с живой кожей: указывать детали вроде пор, веснушек и направления света (например, мягкий свет из окна слева) и фокусное расстояние объектива (85mm f/2) для получения журнальных кадров.
  • Кинематографичные сцены и арт: создавать анаморфотные кинокадры с контровым освещением или переключаться на художественные техники (например, акварель), убрав из промпта параметры камеры и исключив стиль из негативного промпта.
  • Сцены с короткими надписями: добавлять вывески или текст на объектах, заключая нужные слова в кавычки внутри описания.

Пример

Промпт: Close-up portrait of a 34-year-old Nigerian woman with deep brown skin, natural coily hair pulled back, small gold hoop earrings, looking straight into the lens with a calm, confident expression. Soft window light from the left, a gentle falloff into shadow on the right side of her face, visible pores, fine vellus hair on her cheek and a subtle natural sheen on her forehead. Neutral warm-grey background, 85mm lens at f/2, shallow depth of field, high-end editorial portrait photography.

ПодробнееОбучение: 6 эпох на разрешении 1024px на датасете из более чем 20 000 отобранных фото и кинокадров (выбрана версия 4–5 эпох через KohakuMossTrainer).
Сборка в ComfyUI: весы в models/diffusion_models/, отдельно нужны Text Encoder (qwen3.5_9b_bf16.safetensors или qwen3.5_9b_w4a8_gptq) и VAE (flux2-vae_small.safetensors).
Настройки генерации: Sampler Euler, 30 шагов (25–50), CFG 3, Shift 5, Skip Layer Guidance на Layer 22.
Ограничения V1: сложные позы рук, мелкий или длинный текст, лица в больших толпах и некоторые арт-стили могут получаться с артефактами.
Примеры
Discuss 130 1.3K

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 5.0 GB · ready files7.0 GB
  • FP8 / INT8recommendedweights 2.5 GB4.3 GB
  • 4-bitweights 1.4 GB3.1 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 5060 Ti 8GB

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

A ready script for the machine we advise above: paste it and the model downloads and starts.

  1. 1. Rent A30

    $0.26 an hour with the coupon. Pick the Ubuntu image when you create the machine.

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    #!/usr/bin/env bash
    # 3042282-juggernaut-moss
    set -e
    # ===== Tokens: paste yours between the quotes =====
    export CIVITAI_TOKEN=""   # civitai.com/user/account → API Keys, for Civitai LoRAs
    # ==========================================
    # NVIDIA driver: CUDA 13 needs 580+. If older or missing, the current nvidia-open is installed (keep yours: KEEP_DRIVER=1)
    DRV=$(nvidia-smi --query-gpu=driver_version --format=csv,noheader 2>/dev/null | head -1 | cut -d. -f1)
    case "$DRV" in ""|*[!0-9]*) DRV=0 ;; esac
    if [ "$DRV" -lt 580 ] && [ -z "${KEEP_DRIVER:-}" ]; then
      . /etc/os-release && \
      curl -fsSLO "https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${VERSION_ID//./}/x86_64/cuda-keyring_1.1-1_all.deb" && \
      sudo dpkg -i cuda-keyring_1.1-1_all.deb && rm -f cuda-keyring_1.1-1_all.deb && \
      sudo apt-get update && \
      sudo DEBIAN_FRONTEND=noninteractive apt-get install -y nvidia-open || \
      { echo "Could not install the NVIDIA driver: see the error above. To keep the current one, run with KEEP_DRIVER=1."; exit 1; }
      echo "NVIDIA driver updated. Reboot the machine (sudo reboot) and run this same script again."
      exit 0
    fi
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    # CUDA 13+ → int8_convrot (Comfy-Org's advice), else fp8_scaled
    CU=$(nvidia-smi | grep -oP 'CUDA Version: \K[0-9]+' || echo 12)
    [ "$CU" -ge 13 ] && TORCH=cu130 || TORCH=cu128
    [ -d ~/ComfyUI ] || git clone https://github.com/comfyanonymous/ComfyUI ~/ComfyUI
    cd ~/ComfyUI
    uv venv --python 3.12 --allow-existing && source .venv/bin/activate
    uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$TORCH
    uv pip install -r requirements.txt "huggingface_hub[cli]"
    civitai() {  # civitai <model id> <folder>: the newest version of a Civitai model
      vid=$(curl -fsSL "https://civitai.com/api/v1/models/$1" | python3 -c 'import json,sys;print(json.load(sys.stdin)["modelVersions"][0]["id"])')
      (cd "$2" && curl -fL -OJ -H "Authorization: Bearer $CIVITAI_TOKEN" "https://civitai.com/api/download/models/$vid")
    }
    # Base files: MOSS Image Base, 8-bit
    if [ "$CU" -ge 13 ]; then
      hf download Comfy-Org/MOSS-Image text_encoders/qwen3.5_9b_int8_convrot.safetensors vae/flux2-vae.safetensors --local-dir models
    else
      hf download Comfy-Org/MOSS-Image text_encoders/qwen3.5_9b_w4a8_gptq.safetensors vae/flux2-vae.safetensors --local-dir models
    fi
    # Main model: 3042282-juggernaut-moss
    civitai 3042282 models/diffusion_models
    # Start ComfyUI. From your computer: ssh -L 8188:localhost:8188 user@IP, then http://localhost:8188
    python main.py --listen 127.0.0.1 --port 8188
  3. 3. Use it

    From your computer: ssh -L 8188:localhost:8188 user@machine-IP, then open http://localhost:8188. Or open that address in the browser on the machine's desktop. The model's workflow is usually in its Hugging Face card.

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • SageAttention 3v2.2.0from October 28, 2025

    even faster on RTX 50 / Blackwell

    FP4 attention for Blackwell. Faster than SageAttention 2, but the authors suggest v2 when accuracy matters.

    How to enable: Build from the sageattention3_blackwell folder of the repo; in ComfyUI via KJNodes.

    Earlier generations (2)
    • SageAttention 2++ — Quantised (INT8/FP8) attention with no visible quality loss. The main speed-up for image and video generation.
    • SageAttention 1 — First version: INT8 for Q·K. Still works, but 2++ is faster and more accurate.
  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (3)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
    • xFormers — The older way to speed up attention, works almost everywhere. Sage or Flash are faster where available.
  • cache-dit (DBCache)v1.5.6from November 20, 2026new release

    1.5–3× at nearly the same quality

    Reuses block outputs between diffusion steps. Supports most DiT models.

    How to enable: pip install cache-dit; one line cache_dit.enable_cache(pipe) for diffusers.

    Earlier generations (2)
    • MagCache — Skips steps by magnitude of change. More accurate than TeaCache, no calibration.
    • TeaCache — The first popular diffusion step cache. Works, newer methods are more accurate.
  • Nunchaku (SVDQuant 4-bit)v1.2.1from January 25, 2026

    ≈3× faster and 3.5× less memory

    4-bit versions of popular image models with almost no quality loss (FP4 on RTX 50).

    How to enable: Ready weights for supported models; in ComfyUI use ComfyUI-nunchaku.

  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

  1. MOSS-Image-Basefamily root
  2. MOSS-Image-SFT
  3. 3042282-juggernaut-moss

New posts about versions of MOSS-Image-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face
Merges 2All on Hugging Face

About the model

civitai/3042282-juggernaut-moss
Author
KandooAI
Category
Images
Released
Posted

On NeyroLearn

Civitai

1.3K130

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments