Skip to content
Other

Kandinsky6-VSR-LoRas

LoRA для более чёткого апскейла x2

1 min readupdated

LoRA k6_sr_v5_x2_crisp от MachineDelusions для дистиллированной 2-step модели Kandinsky 6 VSR. Это rank-32 адаптер, который делает апскейл x2 резче: добавляет более чёткие края и мелкую текстуру, но может сильнее отклоняться от исходного изображения.

Ключевые особенности

  • Rank-32 LoRA для дистиллированной 2-step Kandinsky 6 VSR.
  • Даёт более чёткие края и мелкую текстуру при апскейле x2, но снижает верность исходнику.
  • Работает через ComfyUI-нодпак FL Kadinsky Upscale; файл кладётся в ComfyUI/models/loras/FL_Kadinsky/.
  • Рекомендуемые настройки: Scale 2x, LoRA strength 1.0; на лицах естественнее 0.7, lq_noise_scale — 0.3.
  • Обучена только для x2 на unsharp-masked 4K-таргетах с L1, LPIPS, edge/texture и лёгким adversarial loss.

Пример

hf download MachineDelusions/Kandinsky6-VSR-LoRas k6_sr_v5_x2_crisp.safetensors --local-dir ComfyUI/models/loras/FL_Kadinsky
ПодробнееЛицензия MIT, как у базовой модели.
LoRA обучена только под апскейл x2.
Главный компромисс: больше резкости и текстуры против точности передачи исходника.
Для лиц можно снизить силу LoRA до 0.7.
Discuss Telegram 0

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

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.

    # MachineDelusions/Kandinsky6-VSR-LoRas
    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 MachineDelusions/Kandinsky6-VSR-LoRas --local-dir ~/models/Kandinsky6-VSR-LoRas
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to Kandinsky6-VSR-LoRas
  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

New posts about versions of Kandinsky6-VSR-LoRas (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

MachineDelusions/Kandinsky6-VSR-LoRas
Author
MachineDelusions
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