GNU social JP
  • FAQ
  • Login
GNU social JPは日本のGNU socialサーバーです。
Usage/ToS/admin/test/Pleroma FE
  • Public

    • Public
    • Network
    • Groups
    • Featured
    • Popular
    • People

Image: ['pelicans-on-bicycles-veo2.jpg'] Prompt: <|im_start|>system You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|> <|im_start|>user describe this<|vision_start|><|image_pad|><|vision_end|><|im_end|> <|im_start|>assistant Alright, I've got this "Text to Video" tool to explore. It seems pretty advanced, allowing me to turn text descriptions into actual videos. The interface looks user-friendly, with a dark theme that's easy on the eyes. On the left side, there's a panel where I can input my text prompt. It already has an example filled in: "A pelican riding a bicycle along a coastal path overlooking a harbor."

Download link

https://cdn.masto.host/fedisimonwillisonnet/media_attachments/files/113/712/054/445/643/600/original/29b71bc8e707b240.png

Notices where this attachment appears

  1. Embed this notice
    Simon Willison (simon@fedi.simonwillison.net)'s status on Friday, 27-Dec-2024 04:22:37 JST Simon Willison Simon Willison
    in reply to

    I got QvQ running on my (M2 64GB) laptop!

    uv run --with 'numpy<2.0' --with mlx-vlm python \
    -m mlx_vlm.generate \
    --model mlx-community/QVQ-72B-Preview-4bit \
    --max-tokens 10000 \
    --temp 0.0 \
    --prompt "describe this" \
    --image pelicans-on-bicycles-veo2.jpg

    https://simonwillison.net/2024/Dec/24/qvq/#with-mlx-vlm

    In conversation about 4 months ago from fedi.simonwillison.net permalink
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.