Skip to content

AI helper ​

Works with Premiere Pro 2021+ Works with After Effects 2021+ Works with DaVinci Resolve 18.0+

"AI helper" in the LmBox Bridge desktop app (sidebar label , route openaiChat) is a full chat page in the Tauri shell — not the old CEP panel inside the editing app. The chrome shows the connected host (DaVinci Resolve / Premiere / After Effects, and so on). The bottom bar switches among Chat / Agent / Images / Video, and picks Official cloud → Golden key or a Keychain model.

What you will learn

  • Open AI helper from the desktop sidebar (or a Scaffolding slot)
  • Switch mode, provider and image/video parameters in the bottom bar
  • Read the mode · provider · model tag on each reply
  • Save or import results, and understand common failure toasts

Guide scope

This is the main lab guide for the current desktop UI. The old CEP “home → Lab → AI helper” path is no longer the primary story; if you still see that wording elsewhere, prefer this page.

What it solves ​

PainHow this page helps
Need workflow, copy or planning help while editingChat / Agent via Official cloud or your own models
Need stills for mood or reference on the timelineImages with aspect and size; save or import to the host
Need a short motion sampleVideo with aspect, duration and resolution; player in the card
Want to try without your own API keyOfficial cloud → Golden key (sign-in; caps and entitlements apply)
Already have an OpenAI-compatible endpointAdd it in Keychain, then pick it in the bottom cascader

Before you start ​

  1. Use the LmBox Bridge desktop app (not the retired plug-in-only installer).
  2. Light up the host icon in the sidebar (Premiere / After Effects / DaVinci Resolve, …) so import can reach the extension.
  3. Official cloud: sign in first; membership and bottle caps follow on-screen rules.
  4. Own models: add an OpenAI-compatible profile in Keychain (chat / image / video addresses and enabled models as needed).

How to open ​

  • Sidebar: click (#icon-jiqiren).
  • Scaffolding: you can pin the same route-style capability; hosts match openaiChat.plugIn in menu.json (Premiere CEP/UXP, After Effects CEP, DaVinci Resolve, …).
  • You do not need the old “extension home → Lab” entry.

Desktop UI ​

Chat layout: message list above; history / new chat in the top strip; mode, credentials and send in the bottom input shell.

Chat ​

AI helper · Chat

Figure: sidebar AI helper selected; reply tag like Chat · Official cloud · Golden key; bottom bar for mode and provider.

Images ​

AI helper · Images

Figure: tag Images · Official cloud · Golden key; aspect/size such as 16:9, 1280×720; reference-image strip above the textarea.

Video ​

AI helper · Video

Figure: tag Video · 〈Keychain platform〉 · 〈model id〉 (example: another line with doubao-seedance-2.0); embedded player; save / import actions.

Regions ​

AreaRole
Sidebar AI helperOpens this page; chrome shows host context
History / New chatSession drawer (pin, rename, delete, export Markdown); start fresh
BubblesUser prompt + assistant reply; meta line mode · provider · model
Reply actionsRetry, copy, thumbs up / down (per message allow-list)
Image cardSave, zoom, use as reference, import to connected host
Video cardPlayer; save; import to connected host
Bottom shellText; + references in media modes; mode select; Keychain/model cascader; image aspect·long edge / video aspect·duration·resolution; send / stop

Four modes ​

Bottom-left mode select (remembers last choice):

ModeMeaning
ChatGeneral Q&A; Official cloud shows Golden key as the leaf name
AgentEditing-oriented agent flow (may use connected extension tools; finish HITL prompts before typing again)
ImagesImage API path (not the chat stream); prompt required; optional local references
VideoVideo API path; shares Keychain/model memory with the Blueprint video node

TIP

Screenshots usually show Chat, Images and Video; Agent is in the same dropdown when you need it.

Providers and models ​

Cascader level one:

  1. Official cloud → leaf Golden key (chat, agent, image and video, subject to account capability).
  2. Your Keychain (name from Keychain manager) → then an enabled model id.

When creating a Keychain you can pick common presets (OpenAI, DeepSeek, Kimi, Alibaba Cloud Bailian, Volcengine, SiliconFlow, StepFun, iFlytek Spark, xAI, Mistral, Groq, Relay / Other, and more); the base URL fills in from the preset. Image / video need the matching modality configured; otherwise the UI warns that the channel is not set up.

Reply meta:

  • Official: mode · Official cloud · Golden key
  • Keychain: mode · 〈platform〉 · 〈model id〉 (platform comes from that Keychain item)

Image / video parameters ​

Images (default 16:9, long edge 1280):

  • Aspect: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
  • Long-edge presets: 512 / 768 / 1024 / 1280 / 1920 / 2048 (UI shows derived width×height)

Video (default 16:9, 5 s, 720p):

  • Aspect: 16:9, 9:16, 1:1
  • Duration: 5 / 8 / 10 s
  • Resolution: 480p / 720p / 1080p

In media modes, use + above the input to add local reference images (there is a cap; you can also add from a generated still via Reference).

Suggested flow ​

  1. Open AI helper; confirm the host icon is lit if you plan to import.
  2. Pick mode → Official cloud / Golden key or a Keychain model.
  3. For media modes, set aspect (and duration/resolution); add references if needed.
  4. Type the prompt; send with the button or Enter (Shift + Enter for a new line). Use Stop while generating.
  5. On the result: retry / copy / feedback; images also save, zoom, reference, import; video plays, saves, imports.
  6. Manage history in the drawer; export Markdown from the desktop app.

Host and import ​

  • The menu item targets Premiere (CEP / UXP), After Effects (CEP), DaVinci Resolve, and similar; a lit icon means the desktop app is linked.
  • Import uses the same lab footage path as Media Hub: into the current host. Without a connection (or outside the desktop app) you get a connect-first toast.
  • Agent tool calls need the matching host online; while a HITL step is open, the input stays locked until you confirm or cancel.

Limits and failure modes ​

Please note

Model calls cost ongoing usage: Official cloud spends bottle caps; Keychain bills go to your provider. Availability follows your account and provider.

SituationTypical meaning
Official cloud without sign-inSign in first
Membership too lowUpgrade / unlock the required tier
No model / no API keyPick a model in the bar, or set the Keychain API key
Image/video channel missingConfigure that modality on the Keychain, or switch profile
Image timeoutTry a smaller long edge
Video timeoutTry a shorter duration
Import failedConnect the LmBox Bridge extension in the target app
Actions during streamingWait or click Stop

Code blocks can still be copied; runnable script actions need the connected editing extension (follow the button hint). Do not look for the old CEP top-bar “gpt-4.0” model switch described in earlier docs.

Set up your own Keychain ​

  1. Open Keychain in desktop settings.
  2. Add an AI LLM profile; pick a platform preset or Relay / Other.
  3. Fill API Key and base URL (usually through /v1); configure chat / image / video addresses and enabled models as needed.
  4. Back in AI helper, pick the profile in the cascader. Each mode remembers its last Keychain + model; video shares memory with the Blueprint video node.

Video tutorial ​

Video coming soon

Release notes ​

  • 3.3.1 Switch agent permission modes (Plan / Read-only / Standard / Trust).
  • 3.3.1 Side agent can remember preferences and common settings across chats.
  • 3.3.0 Open the side AI helper from the footer anywhere in the app to chat with the agent while staying on the current page.
  • 2.7.0 New Keychains can pick common providers such as Kimi, SiliconFlow, StepFun, iFlytek Spark, xAI, Mistral and Groq; the address fills in once you choose a platform.
  • 1.6.0 Chat and agent modes can use Official cloud / Golden key without your own model key.
  • 1.6.0 Image and video modes can use official Golden key generation (account capability required).
  • 0.2.5 You can configure different models for chat, images, video and related uses, and pick them on this page.
  • 0.2.0 Chat, Agent and Images each remember the last Keychain and model; Video shares memory with the Blueprint video node.
  • Docs 2026-10-22: rewritten for the Tauri desktop UI (sidebar entry, four modes, bottom-bar credentials and media params, result-card actions); CEP panel path is no longer the main guide.