AibubuAibubu
      HomeProjectsAssetsTemplatesTools
      Create
      mcpGuides
      AibubuAibubu
      credits

      Get 20 bonus credits on your first connection

      Generate product images and short videos inside ChatGPT and Claude

      Connect Aibubu's MCP server and let your assistant pick a model, quote the cost, generate and batch the work.

      1. 1

        Connect and approve

        Add Aibubu in your client, sign in, and choose the permissions to grant. History and assets can be switched off.

        Add Aibubu as a custom connector in ChatGPT, then sign in and approve access to the generation tools.

        Server URL
        https://aibubu.ai/mcp
        Connect AibubuRead the setup guide

        No API key needed. Sign in and approve the connection.

      2. 2

        Start with a prompt

        Upload a product image, describe the result, and the assistant quotes the cost before generating.

        See the full setup steps

      Use cases

      Each use case maps to an MCP prompt template you can try in Claude or ChatGPT.

      E-commerce main image of a sneaker on a white background

      E-commerce main image

      Turn one product photo into a marketplace-ready main image, background removed.

      Product image; optional selling points and channel

      Try in ClaudeTry in ChatGPT
      Wireless earbuds in a desk lifestyle scene

      Product scene set

      Build a set of scene images for one product, priced as a batch before submission.

      Product image; optional scene count (default 4)

      Try in ClaudeTry in ChatGPT

      Campaign image to video

      Create a campaign image and turn it into a short video with your duration and aspect ratio.

      Product image; optional duration, aspect ratio, selling points

      Try in ClaudeTry in ChatGPT
      Three ad versions of the same skincare serum bottle

      Ad variants

      Produce several ad variants of one product, with one quote per variant first.

      Product image; optional variant count (default 3) and differentiation

      Try in ClaudeTry in ChatGPT

      What you can do

      Generated product image of a sneaker

      Image generation

      Generate images from a reference and a prompt, then poll or wait for the result.

      Video generation

      Turn a product image into a short video with the duration and aspect ratio you need.

      Editing: background removal and upscaling

      Remove the background to a transparent PNG, and upscale to 2x, 2K or 4K; 2x is free.

      Supported models

      Available models and prices depend on your region; this list reflects what is available now.

      Image models

      • GPT Image 2

        An image model strong at layout and text rendering, with multilingual posters, infographics and image editing.

        3.6 credits / image≈ $0.0394
      • Nano Banana Pro

        High-quality image generation and editing with strong multilingual text rendering, infographics and multi-image composition.

        9.6 credits / image≈ $0.1051
      • Gemini 3 Pro Image Preview

        Gemini 3 Pro Image generates and edits images from prompts and multiple references, renders legible text in many languages and scripts, and outputs at 1K, 2K or 4K.

        9.6 credits / image≈ $0.1051
      • Nano Banana 2

        A fast image generation and editing model with text rendering, mask-based editing and multi-reference consistency.

        5.76 credits / image≈ $0.0631
      • Gemini 3.1 Flash Image Preview

      Frequently asked questions

      Connect Aibubu to your AI assistant today

      Set it up in minutes, then pick models, get quotes and generate images and videos in chat.

      Connect Aibubu

      Links

      Setup guidePrivacy policyTerms of service[email protected]

      Upload in the conversation

      Pick a local image, video or audio file in clients that support MCP Apps; the file goes straight to storage and comes back as a reference asset.

      Choose a model, quote first

      List models, read their parameters, and price a request before anything is charged.

      Batch generation

      Submit up to six image or video tasks at once, with a total quote and per-item results.

      History and assets

      With the history permission, list the generations this connection submitted and the workspace assets, with filters and paging. This permission must be granted separately.

      Gemini 3.1 Flash Image is a fast generation and editing model that accepts multiple reference images and outputs from 0.5K up to 4K.

      4.08 credits / image≈ $0.0447
    1. gpt-image-2-official

      OpenAI's GPT-Image-2 generates and edits images from prompts and reference photos at 1K, 2K or 4K resolution with low, medium or high quality.

      Priced at quote

      2. Video models

      • Seedance 2

        Unified audio-video generation with text, image, video and audio references, producing clips up to 15 seconds with stereo audio.

        Output 474 credits / 1M tokens≈ $5.19
      • Seedance 2 Fast

        A faster Seedance 2 variant for text, reference-image and reference-video generation, built for quick shot iteration.

        Output 651 credits / 1M tokens≈ $7.13
      • Seedance 2 Mini

        A lighter Seedance 2.0 video model that generates audio-video clips up to 15 seconds at 480p or 720p from text, reference images or reference videos.

        Output 414 credits / 1M tokens≈ $4.53
      • Seedance 2.5

        Seedance 2.5 generates audio-video clips up to 30 seconds with multi-round extension, accepts up to 30 images, 10 videos and 10 audio clips as references, and supports timestamp-level editing.

        Output 1,239 credits / 1M tokens≈ $13.57
      • Kling V2.6

        A native-audio video model for text and image input, producing visuals and dialogue in a single generation.

        7.8 credits / second≈ $0.0854
      • Kling V3

        Text, image and first/last-frame video generation with multi-shot output and native audio.

      Text models

      • gpt-5.6-luna
        Input 117.6 credits / 1M tokens≈ $1.29
        Output 705.6 credits / 1M tokens≈ $7.73
      • GPT-5.5
        Input 68.4 credits / 1M tokens≈ $0.7491
        Output 409.5 credits / 1M tokens≈ $4.49
      • gpt-5.6-terra
        Input 27.3 credits / 1M tokens≈ $0.299
        Output 163.8 credits / 1M tokens≈ $1.79
      • gpt-5.6-sol
        Input 54.6 credits / 1M tokens≈ $0.598
        Output 273 credits / 1M tokens≈ $2.99
      • gpt-6-astra
        Input 336 credits / 1M tokens≈ $3.68
        Output 1,680 credits / 1M tokens≈ $18.40
      • glm-5.3-flash
        Input 16.8 credits / 1M tokens≈ $0.184
        Output 53.04 credits / 1M tokens≈ $0.5809
      See all models
      15.3 credits / second≈ $0.1676