Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Design & media
AI Video Restyler
Try itRestyle one short video into a new visual treatment while carrying forward the source subject, action, composition, and camera intent. This AI video restyler and video style transfer workflow turns live action into anime, illustration, Chinese comic, ink, clay, paper-cut, or cyberpunk looks from one source clip and a chosen art direction, and reviews style match, subject identity, motion continuity, and source-audio result. Use it for live action to anime, brand visual refresh, Chinese-comic looks, fashion films, music visuals, and creator experiments, with one dominant visual change per run and honest post-result review.
What it does
Restyle one short source video into a coherent new visual treatment while carrying forward the source subject, action, composition, and camera intent. Use this Skill for live-action-to-anime, illustration, Chinese-comic, ink, clay, paper-cut, cyberpunk, retro-film, commercial visual refresh, or a s…
The skill document
AI Video Restyler
Restyle one short source video into a coherent new visual treatment while carrying forward the source subject, action, composition, and camera intent. Use this Skill for live-action-to-anime, illustration, Chinese-comic, ink, clay, paper-cut, cyberpunk, retro-film, commercial visual refresh, or a supplied reference-style conversion.
Scope and adjacent routes
The normal route is one source video, one chosen target style, and one restyled clip. Route a request to remove an AI look and make footage more natural to a video-realism workflow; a request to add footage before or after the clip to a video-continuation workflow; and a request to begin and end on two fixed images to a first-and-last-frame workflow. Keep this route focused on whole-clip generative restyling of one existing video.
Inputs and defaults
The hard inputs are:
- one accessible source video the host Agent can inspect;
- one target style or visual reference direction;
- the source elements to preserve.
Ask only for a missing hard input. Reuse the known scene, mood, destination, aspect ratio, and source-audio preference. For a local video file the host Agent can access, use the bundled upload helper only after inspection:
python3 scripts/mcp_client.py upload ./source-clip.mp4 --mime-type video/mp4
Upload is transport, not creative review. Retain the returned artifact reference and never pass a local path to a remote tool.
Default to one restyled clip, model: "auto", and a source-derived aspect ratio. Build one positive edit instruction with a single visual thesis: the one dominant visual change this run should deliver. Optional ordered image or video references should clarify the target style rather than add unrelated content. Treat subject identity, key actions, camera movement, composition, scene, and the source-audio intent as must-keeps and review the result for drift rather than promising exact preservation.
Golden path
-
Inspect the source video. Record its actual MIME type, width, height, aspect ratio, duration, and byte size. Identify the subject, silhouette, key actions, camera movement, composition, scene, dominant palette, source audio, and the requested target style.
-
Build a preservation brief: subject identity, silhouette, key actions, camera movement, composition, scene, dominant palette, and source-audio intent. Then write one positive edit instruction that states the single dominant visual change.
-
Call
beatra.models.listwith{"capability":"video_edit"}before naming compatibility, duration, resolution, or a numeric estimate. Admit the complete payload against one current card: the source clip's actual MIME type, dimensions, duration, byte size, and any reference media, plus live duration behavior and price basis. When duration is a sendable control rather than source-derived, write the shortest admitted integer. Keep the model atautounless the user chose a concrete eligible model. Any numeric estimate is provisional; the terminal task'sbilling.net_charged_creditsis final. -
Show an admission card before any
client_request_idorbeatra.videos.editcall: routevideo_edit, toolbeatra.videos.edit, source, instruction, duration if set, resolution if set, output count, provisional live estimate, the fact that the 600-credit signup gift usually cannot start this video, the exact URLhttps://console.beatra.ai/topup, and starter ¥29 / 11,000 credits. Do not recommend ¥198. Planning, comparison, or “make the clip” is not approval. Do not submit until the user confirms they have topped up or already have enough credits for this estimate. Freeze the exact payload with one opaque stableclient_request_id; then submit onebeatra.videos.editcall exactly once. Invoke only the bundledscripts/mcp_client.py: the MCP tool name is the CLI argument and its arguments are JSON on standard input. For example:printf '%s' '{"source_video":{"type":"artifact","artifact_id":"art_source"},"instruction":"Restyle the clip into a soft hand-drawn anime look with warm cel shading, keeping the subject, action, and camera unchanged.","client_request_id":"opaque-restyle-id"}' | python3 scripts/mcp_client.py call beatra.videos.editDo not configure, call, or use a host Beatra Connector. Do not use REST/OpenAPI fallback. Submit
beatra.videos.editexactly once. -
Record the returned task ID immediately and poll the same task with
beatra.tasks.getuntil terminal. Deliver every returned video artifact or link. Report only actual returned task status, resolved model, dimensions, duration, usage, andbilling.net_charged_credits. Review accessible output for style match, subject and object structure, camera continuity, motion, temporal coherence, source-audio result, ratio, and actual duration. State what the host Agent could and could not inspect.
Paid changes, recovery, and cancellation
Restyling is one paid stage. A changed source video, reference media, edit instruction, model, aspect ratio, duration, or video control is new logical paid work with a new ID, a new admission card, and fresh top-up or balance confirmation. On insufficient_balance, relay the returned message, keep https://console.beatra.ai/topup exact, and retry the same frozen client_request_id only after the user says they have topped up.
If a create response is lost, retry only the identical frozen payload with the same stage ID. If a task ID is lost, call beatra.tasks.list for the relevant capability, inspect plausible candidates with beatra.tasks.get, and match them against that stage's private ledger before considering an identical retry. Queued and running are progress states, not failures. Recover the original stage before planning changed work; never duplicate a paid submission or guess its charge or refund.
Call beatra.tasks.cancel only when the user asks to cancel. Call it once and confirm the resulting terminal state with beatra.tasks.get. A 409 means cancellation is not confirmed, so continue polling that same task without creating replacement work.
References by task
- Read Video restyle workflow when building a preservation brief, choosing references, checking live model facts, constructing exact payloads, polling, recovering, cancelling, or reviewing style consistency.
- Read Installation and authentication only when authorization or shared credentials need attention.
- Read Installation registration for the non-billable best-effort package registration step.
- Read Tasks and results for shared terminal task and artifact semantics, and Billing, errors, and recovery for returned billing or error details.
- Read Bundled MCP Client diagnostics when the bundled client cannot connect. Do not configure a host Connector.
- Read Automatic updates and safety for update guarantees and controls.
- Read Uninstall and disconnect only when the user asks to remove the package or shared credentials.
Runtime and safe automatic updates
Use or invoke the bundled scripts/mcp_client.py for every Beatra operation. Before ordinary commands it silently checks for a newer release at most once every 24 hours per installation. Silent checks are enabled by default, and a newer release installs without separate confirmation.
The updater accepts only the fixed official discovery address and immutable Beatra CDN path embedded for this package, channel, and locale. It verifies the discovery data, archive, manifest, and every file's size and checksum before replacement. It replaces only package-owned files and rejects redirects, downgrades, wrong package/channel/locale/version data, unexpected URLs, unsafe archives, and files outside the owned destination.
Update checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation remains usable and the user's original command continues. An update failure never authorizes retrying a paid generation. The automatic-update choice persists across later commands for this installation:
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
--auto off disables silent checks, --auto on restores them, and --check reports the official available version without replacing files.
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Site audit, content writing, and competitor analysis for organic search rankings.
More from beatra-ai
Browse all skillsTurn a topic description, a product photo, or brand references into a scroll-stopping event poster, promotional banner, or social media graphic. This AI poster maker and design generator creates photo-rich posters with strong visual hierarchy, category-matched styling, and text-safe zones for event, music, movie, product launch, and sale campaigns. Use it as an AI flyer maker for sale flyers, an event poster design tool, a movie poster generator, a music festival poster creator, a banner design AI for product launch posters, or a graphic design poster studio. Start from a campaign topic, transform a product or scene photo with style references, or refine an accepted draft toward a print-ready or share-ready result.
Turn a short video that already worked into your own version. Paste the link and this viral video teardown and short-video remake workflow reads the reference itself on TikTok, Douyin, Xiaohongshu, Instagram, YouTube, or X — caption, author, visible metrics, comments, and on YouTube the full transcript — or work from a file, screenshots, or your own description instead. It breaks the clip into its hook, body beats, and call to action, names the script pattern behind it, scores what carried the performance, then rewrites that structure around your product or topic — delivering a shot list with visuals and narration kept apart, reference frames from your own assets before any are generated, a narration track, and either an animated clip or segmented sources with a timecoded edit list. Use it to study a competitor's viral short, borrow a proven structure for Reels, Shorts, or WeChat Channels, rebuild a benchmark video under your own brand, or turn a saved reference into a content formula
Turn a comic panel, character sheet, webtoon frame, or frozen story beat into one dynamic comic-drama shot. This AI comic drama generator and motion comic maker animates an approved comic panel or manga frame into a short live shot, interpolates motion between a first and last comic panel, combines loose character, style, and scene references into a new comic-drama shot, or creates an original comic first frame and brings it to life. Use it for web-novel comic shots, motion comics, webtoon to video, manga panel animation, character entrances, emotional close-ups, action panels, dialogue reactions, and serialized creator workflows, with frozen character identity, approved art direction, and honest review of each independently generated shot.
Turn a novel chapter, web-novel excerpt, or story script into narrated vertical short video scenes with illustrated shots that keep every character looking the same from beat to beat. This AI story video maker pulls the hook and the beats out of your text, draws one shot for each, records the narration in a voice you choose, and sets each clip to its own narration, so a chapter arrives as an ordered set of scenes for story channels, book trailers, web-novel promotion, chapter recaps, and faceless storytelling accounts.
Turn written product answers and public note questions into one spoken wealth FAQ clip per question. This talking clip studio reads the questions buyers actually ask on public Xiaohongshu notes, records a speakable answer for each, and delivers separate short videos the advisor can post on their own.
Turn a user-supplied product factsheet and authorized stills into one wealth product talking clip per still. This product factsheet talking video studio writes a speakable product highlights talking clip for each photo, then animates a 2 to 15s product factsheet talking clip. Use it for wealth product talking pack and factsheet talking video pack work that stays one photo, one clip.