Skip to content
Other

Pen Sketch Style v1

хаотичный шариковый скетч для MOSS-Image

1 min read

LoRA от colinurbs для OpenMOSS/MOSS-Image переносит стиль чёрного шарикового рисунка на белой бумаге: запутанные петли и линии создают тон. Это MOSS-Image-версия Flux-LoRA Pen Sketch Style; ранг 64, alpha 16.

Ключевые особенности

  • Стиль: хаотичные чёрные линии шариковой ручкой по белой бумаге.
  • Промпт начинается с триггерной фразы, затем описание объекта; короткий вариант тоже работает.
  • Запросы на фото остаются фото — стиль не навязывается.
  • Версия v1: шаг 1 000 из прогона, остановленного примерно на 2 200.
  • Обучение: kohya sd-scripts, 4070 Super, INT8 + block swap, 428 изображений и 1 284 обучающих элемента.

Пример

Пример из карточки (seed 42, 896×1280, 30 steps, CFG 3): A pen-people scribble drawing in black ballpoint ink on white paper. A tabby cat stretching on a windowsill next to a potted geranium.

ПодробнееLoRA rank 64 / alpha 16, lr 2e-4 с warmup 200 шагов и cosine decay, batch 1, бакеты 1024 px.
Датасет: 428 изображений, у каждого длинная, средняя и короткая подписи — 1 284 элемента.
Ограничения: иногда появляется фальшивая подпись в углу; тестировали только на обучающих сэмплах — 8 промптов, один seed.
Файл: pen_sketch_moss_v1.safetensors (v1, шаг 1 000).
Discuss Telegram 0

Will it run?

Working out the memory needs

This is a LoRA: it only runs on top of the base model OpenMOSS/MOSS-Image-Base. The base model's size is still being collected; the estimate will appear within a day.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    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.

    # colinurbs/moss-pen-sketch-lora
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download OpenMOSS/MOSS-Image-Base --local-dir ~/models/MOSS-Image-Base
    hf download colinurbs/moss-pen-sketch-lora --local-dir ~/models/moss-pen-sketch-lora
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to MOSS-Image-Base
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

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/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.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

colinurbs/moss-pen-sketch-lora
Author
colinurbs
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments