Updated 2026-11-19 · no install · your own clip · 5–30 s · photo or anime character

Open Genjutsu in Your Browser — Swap the Person in a Clip, No GPU

Open Genjutsu on Genjutsu AI, an independent site, is a no-install open-source-style character swap: upload a clip and a photo, and Seedance 2.5 redraws the person you name.

你想改什么?

把主要人物或角色换成你图片中的角色。动作、运镜和节奏保持不变。

参考图0/9

在指令中输入 @ 选择图 1、图 2 或视频 1。 JPG、PNG 或 WebP · 最大 10 MB · 每边 300–6000 px。

46/20000

Seedance 2.5 直接编辑你的视频,动作、运镜和构图最贴近原片。最长 30 秒。

视频时长
10 秒
5 秒30 秒
分辨率

输出:16:9 · 1280×720

消耗 175 积分

你上传的内容不会被公开,仅提供给视频服务商用于审核和生成。 隐私政策

片段起始时间00:00 – 00:10
00:0000:00

你的视频不会被公开。竖屏、方形和横屏视频都会保持原画幅;点击生成后才开始上传。

  • No GPU or ComfyUI
  • Your own MP4 or MOV
  • Original sound kept
  • From 39 credits

Open genjutsu on Genjutsu AI is a hosted editor, independent of Higgsfield and the GitHub projects below, so you need no NVIDIA card, ComfyUI or API key: upload an MP4 or MOV, pick 5 to 30 seconds, add a character photo. A swap costs from 39 credits (about $1.45); new accounts get 3 free credits, not enough for one. The 480p–1080p MP4 has the clip’s original sound, watermarked until your first purchase.

How open genjutsu works here

  1. 01

    Upload the video and pick the seconds

    Upload my video is already selected: add an MP4 or MOV up to 5 minutes long and 50 MB, then slide to the 5 to 30 seconds you want. Nothing is installed or downloaded.

  2. 02

    Add the character photo and say who it replaces

    Keep the change type on Character, add a photo or drawing of the new character (up to 9 images, 10 MB each) and edit the instruction so it names who in the clip each image replaces, for example “the woman in the yellow coat”.

  3. 03

    Check the price and generate

    Seedance 2.5 edits the clip itself on our servers. The button shows the exact credits first, and the finished MP4 carries the selected seconds’ original sound.

Character swap examples: original clip and result

Each pair shows an original clip on the left and its character swap on the right: one person, a couple and a trio, each replaced by new characters while the setting and the framing match. The clips are silent, landscape and 13 to 14 seconds long.

原片

换角色后

One person swapped for a 1920s aviator character

A woman in headphones talking to a selfie camera on a forest road is swapped for an aviator in a leather flying helmet, goggles and a sheepskin collar. In the swapped clip the head turns, the forest and the framing match the original. 14 秒 · 横屏 · 无声。

原片

换角色后

Two dancers swapped for two flamingo characters

A ballroom couple practising in a mirrored studio is swapped for two flamingo characters, one in a white shirt and one in a coral gown. In the swapped clip the hold, the turns and the studio match the original. 14 秒 · 横屏 · 无声。

原片

换角色后

Three dancers swapped for tin toy characters

Three dancers under stone arches are swapped for two toy soldiers and a ballerina doll. In the swapped clip the routine, the three positions and the arches match the original. 13 秒 · 横屏 · 无声。

Which open genjutsu GitHub project is which?

Open genjutsu is not one program: the name covers several GitHub projects that copy Higgsfield Genjutsu’s video character swap. D3voz/openjutsu runs open model weights on your own NVIDIA card through ComfyUI; Anil-matcha/open-genjutsu and abdullayevziyodulla/open-genjutsu are local apps that send each job to Seedance 2.5 or Wan through paid API accounts you bring; Comfy-Org/comfy-openjutsu is the code behind the hosted Openjutsu app on Comfy’s platform.

ProjectWhere the video is madeWhat you needClip limitsCost per video
D3voz/openjutsu (about 2,500 stars)Your PC: MiniMax H3 open weights, SAM 3.1 tracking, Qwen3-VL captions, all in ComfyUIAn NVIDIA card (tested on a 16 GB RTX 4060 Ti with 64 GB of RAM), ComfyUI, custom nodes and model downloadsWhole clip or a chosen part; 6 s at 480p took about 6–13 min in testingNo per-video fee; electricity and your hardware
Anil-matcha/open-genjutsu (about 1,200 stars)A hosted API: Seedance 2.5 Omni Reference, or Wan 3.0 for the Lite optionPython 3.10+, FFmpeg and an API key with generation creditsSource 4–15 s, 50 MB; up to 8 character images; output 4–30 sPaid to the API account; preparation steps (depth, frames, character sheets, prompt) are billed too
abdullayevziyodulla/open-genjutsuHosted providers you pick: Seedance 2.5 or Wan 2.2 AnimatePython 3.12+, Rubber Band and your own provider keys480p draft or preview, then a 720p or 1080p render depending on providerApp free; preparation and every render billed to your provider accounts
Comfy-Org/comfy-openjutsuA Comfy cloud deployment running MiniMax H3A Comfy Developer Platform account, an API key and a GPU deploymentMP4 or MOV up to 100 MB; a 5–15 s partDeployment credits while the GPU runs
Genjutsu AI (this page)Our servers: Seedance 2.5 edits your clip, then the original sound is put backA browser and an account; no install, GPU or keyMP4 or MOV up to 50 MB; a 5–30 s part; up to 9 photos39–928 credits (about $1.45–$34.50), shown before you generate

Facts for the four projects are taken from their own README files and repository pages, checked 19 November 2026; star counts change daily. All four are MIT licensed, but the model files have their own licences: D3voz/openjutsu notes that its face-fix step uses InsightFace buffalo_l (non-commercial research only) and Ultralytics YOLO weights (AGPL-3.0). Forks and copies with similar names, such as other “openjutsu” and “open-genjutsu” repositories, are not listed here. Genjutsu AI is not one of these projects and is not affiliated with their authors.

Is open genjutsu free?

Open genjutsu is free to download but not always free to run. D3voz/openjutsu has no per-video fee once you own a capable NVIDIA card; the two API-based open-genjutsu apps are free and MIT licensed, yet every preparation and render step is billed to your own provider account. The browser editor on this page charges credits per swap instead, with the price shown before you generate.

On Genjutsu AI, the cheapest swap is 39 credits (about $1.45) and the 3 sign-up credits do not cover one on their own. Uploading, trimming, adding photos and seeing the price cost nothing. Swaps from accounts without a purchase carry a moving genjutsu-ai.app watermark; any purchase unlocks clean downloads, including earlier videos.

QuestionWhat happens here
Price per swap39 to 928 credits (about $1.45 to $34.50 at the lowest credit price), set by the model, the resolution and the seconds you select. A 10-second swap on Seedance 2.5 at 480p is 78 credits (about $2.90).
Free credits3 sign-up credits, valid for 7 days. Not enough for a swap on their own: the cheapest is 39 credits. Uploading, trimming and seeing the price cost nothing.
Smallest purchaseThe $5 Trial pack (one-time) has 24 credits, not enough for one swap. The smallest one-time pack that covers one on its own is $12 for 220 credits. The cheapest start from zero is the $9 Starter plan, a monthly subscription with 240 credits a month.
WatermarkSwaps from accounts without a purchase carry a moving site watermark. Any purchase unlocks clean downloads of earlier and later videos.
Failed or rejectedIf the model fails, or its review turns down a photo or the clip, the credits go back automatically; an upload stopped by the safety check is never charged. If the model has delivered and only adding the sound back or exporting fails, the credits are kept and support finishes the video. A finished swap is not refunded.

Is there an open genjutsu app or download?

Open genjutsu has no official phone app: the GitHub projects are downloaded from GitHub and run on a computer as a local web page in your browser (D3voz/openjutsu has a Windows start script; the open-genjutsu apps start from Python). Genjutsu AI needs no download at all: open this page in a phone or desktop browser, tap Upload my video, pick the clip from your gallery and download the finished MP4 to post it. A long 4K phone video may be over the 50 MB limit, so trim or export it smaller first.

Downloads that promise a packaged “Openjutsu APK” or installer outside GitHub are not from any of these projects and can carry malware.

Pricing and credits for a browser swap

A swap here costs 39 to 928 credits, about $1.45 to $34.50 at the lowest credit price; the resolution and the seconds you select set the price. A 10-second swap is 78 credits at 480p (about $2.90), 175 at 720p and 310 at 1080p. The smallest one-time pack that covers one swap is $12 for 220 credits, or the $9 Starter plan (a monthly subscription) gives 240 credits a month.

模型 · 分辨率5 秒10 秒15 秒30 秒
Seedance 2.5 · 480p3978117233
Seedance 2.5 · 720p88175262523
Seedance 2.5 · 1080p155310464928

Seedance 2.5 bills for the seconds of your clip it reads and again for the seconds it outputs, which is why a swap costs more per second than a text-to-video clip. If the model fails or its review turns down an input, the credits come back automatically; if the model has delivered and only our sound and export step fails, the credits are kept and support finishes the video. More packs and plans are on the pricing page.

What the browser version does not do

The browser editor trades the local projects’ control for no setup: it does not run offline or on your own GPU, it does not let you swap in your own model weights or LoRAs, and it renders at most 30 seconds in one go. The prompt asks the model to follow the clip’s movement and camera; results vary with the clip and the photo, so try a short section first. The usual problem spots, with what helps:

What you may seeWhyWhat helps
The new face changes during a head turn or a spinThe face is hidden or side-on for a few frames and has to be redrawnA sharp front photo plus a three-quarter view; a slower or shorter section
The wrong person is replacedThe instruction did not single the person outName them by side of the frame and clothes at the start of the clip
Small background people look oddTiny figures and reflections are hard to redrawA clip where the person fills more of the frame; avoid mirrors
The model refuses before it startsIts review turned down a photo or the clip; the credits come backA clearer photo of an adult

It does not swap live on a camera, change the voice or write new dialogue or music. For one built-in clip that only needs your photo, see motion transfer; for a fuller guide to replacing a person, see AI character swap; and for what is and is not free across the editor, see the guide Genjutsu AI free.

最近更新: 2026-11-19

Questions about the browser route

Can I run a Genjutsu-style swap on my own RTX 4090 or 5090?

Yes, with the local Openjutsu project (D3voz/openjutsu): it runs open MiniMax H3 weights through ComfyUI on an NVIDIA card, and its author tested it on a 16 GB RTX 4060 Ti with 64 GB of system RAM, so a 24 GB or 32 GB card has more room, mainly for 1080p. You install ComfyUI, its custom nodes and the model files yourself. If you would rather not set that up, the editor on this page does the work on our servers.

How long does one swap take?

On a local RTX 4060 Ti, Openjutsu’s README puts a 6-second 480p clip at about 6 to 13 minutes, and 1080p at about 2.5 times the time of its default 736p. Here the job runs on our servers instead, so your computer does no rendering: the wait depends on the length, the resolution and the model queue, the job keeps running if you close the tab, and the finished video appears in your history.

Does the swap change the voice of the original video?

No. The model redraws the picture only; when the video is exported, the selected seconds’ original recording is put back, so the voice, music and timing are the clip’s own. To change a voice you need a separate voice tool.

Is this the same as Higgsfield Genjutsu?

No. Genjutsu AI is an independent site, not affiliated with Higgsfield or with any of the open-source Genjutsu projects on GitHub. It offers the same kind of edit (your clip plus a character photo, with the clip’s movement as the guide) on Seedance 2.5, priced in credits on this site.

Is this just a deepfake? Can I post the result?

It is AI-generated video, so treat it like one: only swap people who have agreed, never use it to pass someone off as saying or doing something, and label the video as AI-made where the platform asks. You also need the rights to the footage and its music before you post or sell it; do not use real celebrities or characters you do not own in ads.

用任意 AI 助手核实

“Can I use open genjutsu (Openjutsu) in a browser without a GPU or ComfyUI?”

保留这条镜头,改换其中的世界。

选择片段,添加参考素材,几分钟后即可看到编辑结果。生成前会先显示报价。

打开 Genjutsu AI 编辑器