LongCat Video: what it is, where to run it, what it costs

LongCat Video is Meituan's open-source video model (MIT license, October 2025), hosted on fal.ai from $0.005 per generated second; this site is not LongCat and makes images only, never video, and its photo editor, a different model, edits one photo in about 37 seconds for 10 credits. Free with sign-up: 10 credits = 1 image, then from $0.13 per image.

Your edited photo appears here (this site’s editor)
Studio background edit made on this site: the same woman on a plain light-grey studio backdrop
Input photo (AI-generated, fictional): a smiling woman with curly brown hair in a green sweater, in a parkYour photo
Type your own change, or leave this empty and pick a one-tap edit below.0/400

Style changes (cartoon, 3D, anime) are not reliable yet. If the result looks unchanged, try again or describe the change more specifically.

One-tap edits

  • Not LongCat, not affiliated with Meituan
  • Images only: this site does not make or cut video
  • Free with sign-up: 10 credits = 1 image
LongCat-Video release (GitHub README)
Oct 25, 2025
parameters, as listed in the README
13.6B
license for the weights (README)
MIT
per generated second on fal.ai
$0.005–$0.04

What LongCat Video is

From the makers’ README and paper

  • The Meituan LongCat Team lists LongCat-Video as a video generation model with 13.6B parameters. One model covers text-to-video, image-to-video and video continuation.Source: GitHub README ·
  • Released on October 25, 2025: the README news line and the first version of the paper carry that date.Source: arXiv paper ·
  • License: MIT for the model weights and the repo’s contributions. The README adds that it grants no rights to Meituan trademarks or patents.Source: GitHub README ·
  • Image-to-video takes a still photo as the first frame and animates it. The output is a video, not a still image.Source: GitHub README ·

The makers’ claims, not tested by us

  • The makers say it produces 720p, 30 fps video within minutes, and minutes-long videos without color drifting or quality loss. The README gives no exact maximum length, and we did not test it.Source: GitHub README ·
  • The README also compares it with other video models using the makers’ own internal rating. That is not an independent test, so we do not quote the scores.Source: GitHub README ·

Where LongCat Video is hosted

  • fal.ai lists it as text-to-video and image-to-video, at 480p and 720p, each in a standard and a distilled version. Per generated second: standard 480p $0.025, standard 720p $0.04, distilled 480p $0.005, distilled 720p $0.01.Source: fal.ai model page ·
  • Replicate has a community upload by another user (lucataco), not by Meituan. We found no Replicate model from Meituan.Source: Replicate ·
  • For ComfyUI, a community member published converted weights for testing. That is not an official route.Source: Hugging Face (Kijai) ·

Sites that use the name

  • longcatai.net: its footer says it is an independent platform, not affiliated with, endorsed by or sponsored by any model provider or research team. It sells credits and other video models. We found no link to the official repo on its home page and no company name. Treat it as a third-party reseller, not the maker.Source: longcatai.net ·
  • longcat.chat: a chat and coding-agent site for Meituan’s LongCat language models, not a video generator. It is served from Meituan’s infrastructure, so we infer it is Meituan’s; the video README does not link it, so that is not confirmed.Source: longcat.chat ·

Other LongCat names, so you pick the right one

  • LongCat-Flash-Chat is a Meituan language model (560B total parameters). LongCat-2.0 is a larger language model (1.6 trillion total parameters) for coding and agents. Neither makes video or images.Source: Meituan LongCat on GitHub ·
  • LongCat-Image is a separate open image model (6B parameters, Chinese and English). It is not the same as LongCat-Video, and this site does not run it.Source: Meituan LongCat on GitHub ·
  • LongCat-Video-Avatar makes audio-driven talking-person video. It is a separate model in the same repo, not the base video model; version 1.6 is listed in the README news on 2026-11-15.Source: GitHub README ·

Not confirmed

  • Why the name is searched more now: no source we read says. We do not guess.Source: GitHub README ·
  • Hardware needs for running it yourself: the README states no GPU or memory requirement, only demo commands, so we quote none.Source: GitHub README ·
  • The official project page could not be read by our fetcher (it returned nothing), and we found no official web app for the base video model.Source: Project page ·

Prices

LongCat Video prices on fal.ai, and this site

fal.ai’s listed price per generated second, read on 2026-11-18; fal.ai sets these, not Meituan. This site makes no video; its numbers come from its own settings.
-LongCat Video (fal.ai)This site (photo editor)
What it makesVideo, from text or from one photo as the first frameAn edit of one photo you upload (1024 × 1024)
480p, standard$0.025 per generated secondVideo not offered
720p, standard$0.04 per generated secondVideo not offered
Distilled, 480p and 720p$0.005 and $0.01 per generated secondVideo not offered
One edited photoNot what it does10 credits, from $0.13

Where to run it

How to run LongCat Video

  1. On your own GPU: the open weights

    Download meituan-longcat/LongCat-Video from Hugging Face and follow the README: a Python 3.10 environment with the listed torch and flash_attn versions, then its demo scripts. The README states no hardware requirement.

  2. With an API: fal.ai

    fal.ai lists fal-ai/longcat-video/text-to-video and fal-ai/longcat-video/image-to-video at 480p and 720p, plus distilled versions, billed per generated second.

  3. In ComfyUI: community weights

    A community member published converted weights for testing in ComfyUI with WanVideoWrapper. It is not an official route, so check it yourself before relying on it.

Prompts

Photo edit prompts for this site’s editor

These prompts are written for this site’s photo editor, which edits still images with a different model from LongCat Video. They do not make video.

One prompt per one-tap edit

  • Remove background clutter

    Edit my uploaded photo: remove distracting clutter from the background (stray objects, litter, bins, cables, signs and people in the background) and fill those areas naturally with what is around them. Keep the framing as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Plain studio background

    Edit my uploaded photo: replace the background with a plain, softly lit light-grey studio backdrop with natural soft shadows. Keep the framing as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Professional headshot

    Edit my uploaded photo into a clean professional headshot: a smooth neutral grey-blue background with a gentle gradient, soft even studio light on the face, the same crop or a slightly tighter head-and-shoulders crop. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Fix the lighting

    Edit my uploaded photo: fix the lighting only. Balance the exposure, lift dark shadows on faces, tame blown-out highlights and correct the white balance so skin tones look natural. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Warm golden-hour light

    Edit my uploaded photo: change only the light to warm, low golden-hour sunlight from one side, with soft long shadows and a warm glow, as if taken shortly before sunset. Keep the scene and framing. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Classic black and white

    Edit my uploaded photo into a classic black and white photograph with rich contrast, deep blacks, clean whites and fine film grain. Keep the composition exactly as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Watercolor painting

    Repaint my uploaded photo as a soft watercolor painting on textured white paper, with loose washes and visible brush edges, keeping the same composition. Keep every person and pet recognizable, and do not add or remove anyone. No text, logos or watermarks.

  • Sharpen and clean up

    Edit my uploaded photo: gently sharpen it, reduce noise and compression artifacts, and recover fine detail in hair, fabric and edges, without a plastic or over-smoothed look. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

Pricing on this site

Credit packs or a monthly plan.

Credits come in one-time packs ($4.99 for 50 credits, $9.99 for 120 credits, $19.99 for 300 credits); each image costs 10 credits. Or pick a plan from $9.90 a month (500 credits), cancel anytime.

  • Basic · $9.90/month500 credits a month · about 50 images · $0.20 per image
  • Pro · $19.90/month1500 credits a month · about 150 images · $0.13 per image

Billed every month and renews automatically. Cancel anytime in Settings; you keep the plan until the end of the month you paid for. Each month's credits are for that month; unused ones expire.

Refund policy

FAQ

Questions, answered

What is LongCat Video?

LongCat-Video is an open-source video generation model from Meituan’s LongCat Team, with 13.6B parameters, released on October 25, 2025 under the MIT license. One model does text-to-video, image-to-video and video continuation.

Is this site LongCat Video?

No. This site is not LongCat, not Meituan and not affiliated with either, and it does not run LongCat Video. Its own editor uses a different model: upload one photo, write the change (up to 400 characters) or tap a ready-made edit.

Can I make or cut video here?

No. This site edits still photos only. It does not make, cut or edit video. For video, use LongCat Video itself, run on your own GPU or through a host such as fal.ai.

Can I try something here for free?

Partly: new accounts get 10 free credits after signing in, enough for 1 free image (once per account, valid for 7 days, while the day's new-account gifts last). Each image costs 10 credits, from $0.13 per image on a monthly plan.

How much does LongCat Video cost?

The weights are open under the MIT license. On fal.ai, as read on 2026-11-18, it costs $0.025 per generated second at 480p and $0.04 at 720p, or $0.005 and $0.01 for the distilled versions. Running it on your own GPU has your own hardware cost.

Can I run LongCat Video myself?

Yes, the weights and code are public on GitHub and Hugging Face under the MIT license. The README gives setup steps but states no GPU or memory requirement, so check that before you start.

Are longcatai.net and longcat.chat official?

longcatai.net says in its own footer that it is independent and not affiliated with any model provider, so it is a third-party site. longcat.chat is a chat site for Meituan’s LongCat language models, not a video tool; we infer it is Meituan’s but could not confirm it.

Which LongCat is which?

LongCat-Video makes video. LongCat-Video-Avatar makes talking-person video from audio. LongCat-Image is a separate image model. LongCat-Flash-Chat and LongCat-2.0 are language models for chat, coding and agents.

Just need one photo edited?

Upload it, write the change, and download the result in about 37 seconds.

Edit a photo here

Independent site. Not affiliated with Meituan, LongCat, fal.ai, Replicate or Hugging Face, and this site does not run LongCat Video or make video. LongCat Video facts come from the makers’ and hosts’ own pages, read on 2026-11-18.