AI Product Video & Workflow Updates — Latest Features & Improvements

This release brings a shorter path from a saved product to a creative direction, plus more control when you create several videos through an app or AI assistant.

• Get an idea before you render. In Studio, choose Add product & inspire me, or select a saved product, to receive a short ad concept based on the product and your current settings. Insert it, try another idea, or remove the inserted suggestion while keeping your own brief. Suggestions do not start a video or deduct your video credits.
• Explore jewelry and skincare prompts. The updated jewelry and beauty and skincare pages pair copyable prompts with video examples. Use the available Recreate links to bring an example into Studio. The Promptbook signup adds a confirmation step, PDF delivery, follow-up practice emails, and an unsubscribe option.
• Create product videos in batches through API or MCP. Submit up to 300 products using saved product IDs, product-page URLs, or prepared details and images. Share a brief and settings across the batch, set a credit budget, and optionally begin with a five-item sample.
• Keep the results you like. Pause or cancel future batch starts while admitted work finishes. When you request another attempt, retry failed items or rework only selected results with a revised brief. A full restart is also available. Earlier attempts and cumulative credit usage remain in the history; resuming a paused batch does not retry failures.
• Prepare a generation with your assistant. MCP can now discover the current Studio styles, durations, aspect ratios, quality and voices, list your saved products and available avatars, and use their IDs directly. Saved styles carry their creative instructions into the video brief. Preview estimated credits before rendering, or request two or three Studio variants within a batch budget. The estimate does not reserve credits or create a render.
• Understand a wait or failure. Excess single Lab and Studio API/MCP requests wait for an account slot without reserving credits yet. Failed tasks identify the stage, whether the brief finished, and actual credits used. A completed brief may retain its charge even if the video step fails; a retry hint does not create another paid attempt. Bulk eBay imports and saved image references also have improved handling.
• Reuse and organize finished work. Generation results include project and reusable file IDs. Renew protected download links without rendering again, and rename a project from MCP to distinguish versions. Studio projects are listed consistently with the newest first and clearer category previews.
• Follow batch progress during a conversation. The new MCP batch-wait tool waits for a meaningful update and tells the assistant to continue monitoring until completion or a pause that needs your decision. Bulk and variant requests also support signed webhooks to an external receiver. These webhooks do not restart an idle Claude browser conversation or guarantee a new chat message after the assistant has ended its turn.
• Give administrators clearer controls. Assign access to individual admin modules from a focused permissions panel, recognize accounts with admin access, and inspect email-sequence status and delivery attempts. Examples administrators can also promote an owned project's saved result through MCP and choose its dashboard, Studio and landing-page visibility.

Open Studio · Read the MCP guide · Read the API guide

This week's improvements make it easier to understand what is happening while you create, manage your credits, and find the right way to use v4v.

• See your balance change as you work. Credit totals in Lab, Studio and Workflows now follow actual generation charges and refunds, including concurrent runs, rather than waiting for a manual page refresh.
• Recover the status of the same video. A temporary connection or status-check problem is shown separately from a confirmed generation failure. Use Check status to retrieve the existing run instead of starting another video. A connection error alone does not mean a generation failed or a refund was issued.
• Keep useful download names. New product generations no longer inherit a previous product's video name. Download filenames follow the current project, and Lab downloads preserve the correct file extension.
• Choose credits with more context. The pricing page explains workflow credits, compares the actual packs, and gives examples for smaller tests, campaigns and repeated product work. Referral rewards and one-time top-up credit expiry are explained alongside the existing offers. Generation costs vary with the model, settings and number of attempts; check the estimate before rendering.
• Find the existing Shopify app faster. The Shopify guide now links directly to installation and explains the Shopify-admin workflow for previewing, approving and publishing videos to product media. The web product-URL workflow remains available too.
• Browse clearer help on faster pages. Core pages have fuller FAQs, case-study content is accessible without JavaScript, and landing and mobile pricing pages have improvements to loading and layout stability. You can also opt in to pricing news from the public pricing page without creating an account.
• Give AI tools a fuller reference. The expanded plain-text product guide brings product facts, format guidance and the existing prompt library together for assistants and integrations. Use it alongside the API and MCP guides.
• Make import problems easier to investigate. Failed product-page imports now include better operational diagnostics so support can identify the affected store and failure stage.

Open Studio · Compare credit packs

This week brings more ways to go from a product idea to something you can share.

• Work through ideas with Astra. Open Chat in Lab to ask GPT-6 Astra for a script, explore an ad idea, or ask about an image. You can turn on web search when you need it. The response shows the credits used. Astra is also available in Workflows, so its text can feed the next step of your creative process.
• Try GPT Image 2.5. Flare and Sunburst are available for creating and editing images. Choose a format, resolution, and background, including transparent backgrounds for product visuals. The new models also work in Character and Frame Grid tools.
• Start with an image link. Paste a direct product image URL to add a product, then review its details before creating your video. A full store listing is no longer required.
• Bring in more store listings. Product imports now handle eBay listings across more regional sites and show images more reliably from stores such as Buyaparcel.
• Keep your chosen references. Studio handles selected product photos and avatar references more reliably, and Lab has improved completion handling for image generations.
• Explore 20 real product videos. The new examples gallery pairs product photos with finished videos, from UGC and tutorials to cinematic ads. Watch without signing in and find a direction for your own product.
• Catch up on the blog. Eight new posts cover product showcase videos, AI video templates, creative strategy for ecommerce brands, AI influencers, and tool pricing and alternatives. Browse all articles for the full collection.

Try Chat or Images in Lab

Give your product images more room to work, whether you are preparing an ad or building a repeatable creative workflow.

• Enlarge images with Topaz. Find Topaz in Lab's Images section or add it to a workflow. Choose 2× or 4× enlargement and check the credit estimate before you generate.
• Use v4v through the API. Create an API key in Profile → API Keys, then run Lab models and Studio workflows from your own app or automation. Your existing credits apply, and you can review usage or revoke a key in your profile. See the API guide.
• Connect an AI assistant with MCP. The new MCP preview lets compatible assistants find v4v models, use reference images, start generations, and retrieve the results. Follow the MCP connection guide to connect with your API key.
• Recover from temporary download problems. v4v now retries fetching a finished image or video when the download briefly fails, without starting another generation.
• Understand reference-image errors. Studio and Lab give clearer feedback when a generation service rejects a reference image, so you know what to change.
• Use your codes more easily. Bonus and coupon entry in Profile and Billing is clearer and easier to find.

Open Images in Lab

• Added MiniMax H3 Text, Image, and Reference video workflows to Workflows and Lab, with 768p and 2K output, video and audio inputs, additional reference images, and model-aware credit estimates.
• Cut MiniMax H3 prices in half: 768p dropped from 16 to 8 credits/sec, 2K from 26 to 13 credits/sec, and each additional reference image after the first five free images dropped from 8 to 4 credits. Generated and input video seconds use the selected resolution rate.
• Rebuilt Lab around one cleaner composer. Prompt text, Reference Images, First Frame, Last Frame, and other model inputs now stay inside the main creation area, show their selected state, and reopen their full picker with one click.
• Made controls truly model-aware: duration, aspect ratio, resolution, native audio, and advanced settings now use the options supported by the selected model. Clear, live model pricing, and the final Generate cost stay together in the composer footer.
• Made model discovery faster by keeping current favorites visible and prioritizing MiniMax Text, MiniMax Image, Seedance 2.0, Kling 3.0 Motion, and Kling AI Avatar in More Models.
• Lab now preserves per-model drafts and prompt history, keeps URL and browser navigation in sync, validates only the controls currently in use, and restores saved settings more reliably.
• Expanded Runs so creators can open, reuse, retry, rename, delete, and load more generation history without leaving Lab.
• Added live support chat, bonus and discount code entry, and clearer real-world video estimates across pricing and billing surfaces.

Several product updates have been shipped since the last update on March 12, 2026.

What’s new:

- Added Seedance 2.0 to the workflow canvas for new video generation flows.
- Added a dedicated Ad Videos Builder flow for faster ad creation workflows.
- Added a dedicated Shopify Builder flow for product-focused video ad generation.
- Added email-based registration and login support, so access is no longer limited to Telegram only.
- Added coupon code support.
- Added 4 new Wan 2.7 nodes to the workflow canvas:
- Wan-2-7-text
- Wan-2-7-img
- Wan-2-7-videoedit
- Wan-2-7-ref-to-vid

Workflow improvements:

- Wan-2-7-videoedit now shows both credits per second and total credits directly in node settings.
- When Wan-2-7-videoedit duration is set to 0, pricing now uses the source video length automatically.
- Input connections and node settings were improved for the new Wan 2.7 nodes.

New AI Models Added

We expanded the list of available AI models:

• nano-banana-2
• veo-3.1 ( image → video, text → video )
• Kling-v3-0-motion
• seedream-5.0-lite (image generation)

Nodes Updated

Several nodes now support the new image AI models via provider settings:

• Image Editing
• Text to Image
• Character Generation
• Frame Grid Generation

Users can now choose between multiple image AI providers directly in node settings.

New Nodes Added

veo-3-1-image

Generate video from images.

Features:

• image → video generation
• supports up to 14 input images

veo-3-1-text

Generate video directly from a text prompt.

Kling-v3-0-motion

New motion model for generating animated video from images by adapting same emotion and movings from source video.

Improvements

Auto-random seed for veo-3.1

The veo-3.1 nodes now include an automatic randomizer for the seed value, making it easier to generate unique results.

Node tooltips

Added tooltips for node setting options to help users understand parameters more easily. (Currently available for new nodes.)

Better node placement

When adding a new node to the canvas, it now appears in the center of the screen, so you no longer need to search for it.

Editor navigation improvement

The Exit button in the project canvas editor has been replaced with Back to Project for clearer navigation.

Telegram login messages improved

Improved communication messages in Telegram during login authorization to make the process clearer for users.

Fixes

Get Video Frame node

Improved performance — the node now processes frames faster and more reliably.

More improvements coming soon 🚀

Improvements

Mobile UI fixes

Fixed layout issues where workflow cards and dashboard blocks overflowed the screen on mobile.

Variable helper in node inputs

Typing $ now shows a popup with available internal variables ($now, $today, $rnd, $rnd_hex, etc.).

Click to insert directly into the field, for example: {{$rnd_hex(32)}}

Canvas editor improvements

- Click → open add-node panel
- Click and hold → start connection line

• Added copy/paste for multiple selected nodes.
• Improved + behavior on node outputs:

Smarter node auto-connections

New nodes added from + now automatically connect to the correct input port
(audio → audio, clip → clip, etc.).

Navbar shortcut

Clicking the username + credits block now opens the Profile page.

Dashboard improvement

Added a link to ready workflow templates on the Explorer page.

New Features

Frame Grid Generation — Prompt Gallery

• Added gallery with example prompts and demo images.
• Users can insert prompts directly from the gallery.
• Admin interface added to manage gallery items.

Render node watermark

New optional input: image watermark

Watermark position settings:

• top-left
• top-right
• bottom-left
• bottom-right

New node: Get Video Frame

Extract an image frame from a video clip.

Options:

• first frame
• last frame
• specific frame number

Fixes

Node error handling

Fixed issue where nodes kept spinning after errors or when credits ran out.

New Content Sections

How to Use

• Tutorial posts with images, videos, and workflow links.
• Admin interface added for managing guides.

Project Updates

• Dedicated section for publishing feature updates and release notes.
• Admin interface added.

Both sections are accessible from the footer.