Skip to content
Other

Moss Asian Character

LoRA для японских персонажей под Moss

1 min read

LoRA-модель от fidel1234 для базовой Moss (base или sft), обученная в основном на японских персонажах. Совместима с ComfyUI и предназначена для гибкого контроля кадрирования и ракурсов.

Ключевые особенности

  • LoRA для Moss, обучена через AI-Toolkit.
  • Совместима с ComfyUI; рекомендуемый вес — 0.8–1.0, шаги — 25 (8 для turbo), CFG — 4.
  • Датасет вручную отобран: close-up, medium shot, full-body и разные ракурсы.
  • Workflow и trigger word хранятся в метаданных sample-изображения, а не в .safetensors.
  • Sample PNG можно перетащить в ComfyUI, чтобы подтянуть параметры генерации.

Пример

Загрузите LoRA в ComfyUI и перетащите sample-изображение с тем же именем, что и .safetensors, — интерфейс подтянет workflow, параметры и trigger word. Дальше генерируйте с weight 0.8–1.0, 25 шагами и CFG 4; для turbo-режима рекомендуется 8 шагов.

ПодробнееБазовая модель — MOSS Image Base; LoRA обучена на вручную отобранном датасете.
Рекомендации: weight 0.8–1.0, steps 25 (8 для turbo), CFG 4.
Trigger word и workflow встроены только в метаданные sample PNG, не в safetensors.
Лицензия MIT; также нужно соблюдать Moss Community License и Acceptable Use Policy. VRAM не указан.
Discuss Telegram 2 7.9K

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 9.6 GB · ready files11 GB
  • FP8 / INT8recommendedweights 4.9 GB5.9 GB
  • 4-bitweights 2.8 GB3.6 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 5070

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

This is a LoRA: counted together with its base model MOSS-Image-Base.

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
    # Moss_Asian_Character
    set -e
    # 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/$TORCH
    uv pip install -r requirements.txt "huggingface_hub[cli]"
    # Base files: MOSS Image Base, 8-bit
    if [ "$CU" -ge 13 ]; then
      hf download Comfy-Org/MOSS-Image diffusion_models/moss_image_base_int8_convrot.safetensors text_encoders/qwen3.5_9b_int8_convrot.safetensors vae/flux2-vae.safetensors --local-dir models
    else
      hf download Comfy-Org/MOSS-Image diffusion_models/moss_image_base_bf16.safetensors text_encoders/qwen3.5_9b_w4a8_gptq.safetensors vae/flux2-vae.safetensors --local-dir models
    fi
    # LoRAs (1)
    hf download fidel1234/Moss_Asian_Character nashikomomotsuki_mossv1_28_qfloat8.safetensors --local-dir models/loras/fidel1234__Moss_Asian_Character
    # 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
    Add more LoRAs to MOSS-Image-Base
  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.

  • 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 (2)
    • 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.
  • 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

Requires the base model

OpenMOSS-Team/MOSS-Image-Base

This model is a LoRA / adapter. Download the base model first, then load this one on top.

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

fidel1234/Moss_Asian_Character
Author
fidel1234
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

7.9K2

Ask AI about this model

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

Comments