YOUR CREATIVE WORKSPACE. YOUR AGENT’S TOOLKIT.

One idea.
Images. Video. Sound.

Make images and video in your browser. Connect your AI agent to create images, video, music and speech through MCP.

Sign in with Google · No subscription

Building with an AI agent? Connect via MCP →
AI product photography example
AI lifestyle product shot
Recorded character face lock
AI product scene generation
Recorded character outfit
AI minimalist product setup
AI product in context
Frame from the recorded character video
AI product styling
AI lifestyle photography
AI product showcase
AI scene composition

Generated images and a recorded video frame · made with Photoproduct

ONE IDEA, CARRIED FORWARD

Meet the character.
Then watch her move.

An identity portrait became an outfit reference. That reference fed both a character sheet and a video. The same character then picked up a product photo and spoke for it.

Look at the face and beauty mark: the original portrait on the left, the final video frame on the right. These are the actual outputs from a recorded MCP workflow.

20 credits$2.00 · five successful jobs

Recorded 1 Oct 2026. Historical cost; current estimates vary by model and settings.

Original character portrait with auburn bob and beauty markFinal MiniMax H3 video frame after the character turns back to camera
The starting portraitThe final video frame

MOTION + SPEECH

She turns. She speaks. Still her.

Play the recorded 5.17-second MiniMax H3 video with sound. The outfit reference and a quoted line in the prompt produced motion and speech in one call.

YOUR PRODUCT

Now she holds your product.

The same character, a photo of your product, one call. MiniMax H3 reference-to-video took the character plates and the product shot as references and generated the motion and the spoken line together — 5 seconds, 2K, 13 credits.

Explore all five steps, exact prompts and costs

01 / A REAL MCP WORKFLOW

One character. Across generations.

A fresh model call has no memory of the last one. This recorded workflow carries identity forward with prompt_guide instructions and completed job references.

20 credits

$2.00 total · five successful jobs

Recorded 1 Oct 2026 · historical cost

Original generated face lock with auburn bob and beauty markFinal MiniMax H3 video frame after the character turns back to camera
01 · Original face lock04 · Final video frame

From the original face lock to the final video frame: the character’s face, eye colour, auburn bob and beauty mark remain recognizable.

Playback of saved outputs, not live generation. To create your own, sign in with Google and create an MCP bearer token.

Face lock → outfit → character sheet + video

The sheet and video both use the outfit’s job_ref. The video includes speech; the music bed is generated separately. No image download or re-upload between calls.

No file inputSaved output
Generated face lock: auburn bob, grey-green eyes and a beauty mark

OBSERVED IN THIS RUN

This first plate establishes the character’s face, hair, eyes and beauty mark for the following generations.

STEP 1 / 5 · 1 CREDIT

Face lock

flux-2-pro

A 3:4 identity plate: forehead to upper chest, arms down, hands out of frame. The 12-point face-lock grammar fixes bone structure, hair, makeup and identity markers on a flat 18% gray field with shadowless lighting.

Prompt grammar: prompt_guide · face_lock

Recorded run · parameter excerpt
{
  "model": "flux-2-pro",
  "params": {
    "image_size": "portrait_4_3"
  }
}

RETURNED JOB_REF

job_NeOlT6PjpchlYwtG1KvV5w
Read & copy the full recorded prompt and arguments
Full recorded run arguments
{
  "model": "flux-2-pro",
  "params": {
    "prompt": "A clean cinema-character-reference 3:4 headshot, framed from forehead to upper chest with the face filling most of the frame. A Northern European woman in her early thirties, lean athletic build, fair skin with a cool neutral undertone and a matte finish. Dark auburn hair in a deep copper-brown, cut to a blunt chin-length bob with a centre parting tucked behind both ears, fine baby hairs at the hairline. Strong angular features: high wide cheekbones, a square clean jawline, a straight narrow nose, thin upper lip with a fuller lower lip. Wide-set grey-green eyes, level outer corners. Straight dark brows, natural thickness, low arch. Bare skin register, no visible makeup, no liner, no lash drama. A small flat beauty mark below the outer corner of the left eye and no other facial markings: no freckles, no piercings, no tattoos, no scars. Both arms down at her sides, hands not visible, nothing in frame but head, neck, shoulders and upper chest. Plain black thin-strap camisole, no jewellery, no logos, no graphics. Body squared to camera, head level, neutral relaxed expression, eyes to camera, lips closed. BACKDROP: a single flat 18% neutral gray field, one uniform value at every pixel, corner to corner, no seam line, no gradient, no hotspot, no vignette, no falloff. It is a flat colour field, NOT a photographed backdrop: no surface, no floor, no wall, no corner, no horizon. LIGHT: completely flat shadowless illumination, one enormous soft frontal source at camera position, matched equal fill from camera-left, camera-right, above and below, so both sides read at exactly the same brightness. No key-and-fill ratio, no modelling, no shadow side, no nose shadow, no under-chin shadow, no rim light, no hair light, no kicker, no specular hotspot. Extremely low contrast, even, milky, catalogue-flat. NO SHADOW OUTSIDE THE SUBJECT: no cast shadow, no contact shadow, no drop shadow, no ambient occlusion where the body meets the background, no darkening behind the shoulders, no halo, no edge darkening. Shading exists only on the subject and stops cleanly at the silhouette. No light bleed, no spill, no glow, no bounce, no reflected colour cast on the background. Skin reads matte and velvety with light natural sheen on the high points only, no oily shine, real fine even pore texture, real peach fuzz at the jaw and hairline, subsurface scattering reading as semi-translucent biology. Skin renders at its true tone, never darkened, never pale, never washed-out, never cool-shifted by the background. Never plastic, never doll-skin, never waxy. Even sharpness edge to edge. No depth-of-field falloff, no bokeh, no background blur, no lens vignette, no distortion, no flare, no bloom, no chromatic aberration, no haze. Photographed on a 50mm prime. Photographed, not generated. No text, no letters, no numbers, no watermarks anywhere in the image.",
    "image_size": "portrait_4_3"
  }
}

Pass the full argument object to the MCP run tool. To reproduce the workflow, use your own returned job references; these references identify the recorded jobs.

1 of 5

Recorded costs: 1 + 1 + 1 + 13 + 4 = 20 credits. Current model estimates are available in the live catalog below.

Read the full SingularityByte experiment ↗

What would you make with your first idea?

Start with images in the app, or reproduce the workflow with your agent.

TWO WAYS TO MAKE IT HAPPEN

Make it yourself.
Or ask your agent.

01 / IN YOUR BROWSER

Describe it. See it. Refine it.

Start with a prompt, add reference images if you have them, and use chat to work on the result. Build images and video without writing code.

  • Image generation and reference-based editing
  • Chat refinements, video and motion workflows
  • Your generated work in one account
Open the creative workspace

Sign in with Google · No subscription

02 / THROUGH YOUR AI AGENT

Give your agent the tools to create.

Connect one MCP endpoint. Let your agent discover models, inspect credit estimates and pass a completed job into the next call.

  • Images, video, music and speech models
  • Budget filters and measured model telemetry
  • Chain completed jobs without shuttling files
Explore the MCP connection →

Browse without an account. Sign in and create a token to generate.

START WITH SOMETHING YOU WANT TO MAKE

A campaign. A character.
Your next creative project.

Also make room for photo restoration, virtual staging, person-and-product compositions and fresh social creative.

FROM FIRST PROMPT TO NEXT VERSION

“Make the light warmer.”
Keep working in words.

The first image is a starting point. Change the setting, adjust the lighting or add a prop through chat.

  1. 01

    Start with a prompt

    Describe the image. Add a product, person or other reference if it helps.

  2. 02

    See what takes shape

    Review the generated result and choose what you want to change.

  3. 03

    Refine, then keep creating

    Continue in chat, download the result or explore a video workflow.

Bring an idea to the workspace

An illustrative editing conversation · generated image examples

AI Dialogue

"Show someone drinking from the bottle beside a campfire."

AI generated result
Generated

"Now place the bottle on moss, surrounded by ferns."

AI generated result
Generated

"Show a female athlete drinking from the bottle in a gym."

AI generated result
Generated

"Create a product shot of the bottle on dark black granite."

AI generated result
Generated

"Show a male athlete drinking from the bottle in a gym."

AI generated result
Generated

"Create a winter product shot with the bottle standing in fresh snow."

AI generated result
Generated
Type your refinement request...

YES, YOUR PRODUCT PHOTOS BELONG HERE TOO

Same starting photo.
A different setting.

Give an existing product image a new context for your shop, social feed or campaign. Drag each slider to compare the examples.

The same running shoe on a sunlit terracotta sports court
Sage and cream running shoe against a neutral studio backdrop
Studio
Styled scene

From studio to sunlit court

The same ceramic mug on a walnut café table in warm morning light
Ivory speckled ceramic mug against a neutral studio backdrop
Studio
Styled scene

From studio to café morning

The same leather bag on a station bench in golden afternoon light
Cognac leather weekend bag against a neutral studio backdrop
Studio
Styled scene

From studio to weekend away

Illustrative AI-generated examples. Drag to compare the studio image and styled scene.

Bring a clean reference image and describe the scene you have in mind. Review the result, then refine it in chat.

Create my next product scene
FOR DEVELOPERS & AGENTSSTREAMABLE HTTP / MCP

Let your agent
do the making.

Give your coding agent the power to create images, video, music and speech. Connect Photoproduct as an MCP tool, choose a model, and let it create.

—
models
—
featured
—
MCP tools
See the recorded image → video + audio workflow ↑

01 / SET A BUDGET

Price before you create.

Use list_models with max_credits to shop within a budget. Estimates are in whole credits, with input-dependent and variable-length prices labelled.

02 / CHOOSE WITH CONFIDENCE

Real results, honest signals.

The MCP catalog reports success_rate and p50_seconds. Missing values mean unmeasured, never a hidden zero.

03 / KEEP CREATING

Chain jobs, skip the downloads.

Pass a completed job_ref or its public output URL into the next job’s file input. Build image-to-video workflows without shuttling bytes.

One endpoint. Your workflow.

Sign in, open Account → Agentic AI, and create a bearer token. Save it when it appears: tokens are shown only once.

Add this config to a client that supports remote HTTP MCP servers and Authorization headers. Replace YOUR_TOKEN with your token.

MCP quotes use $0.10 per credit, rounded up to whole credits. Your pack’s purchase price is shown in pricing. Parameters and inputs can change a model’s estimate.

MCP client config
{
  "mcpServers": {
    "photoproduct": {
      "url": "https://photoproduct.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}
Example tool call
{
  "jsonrpc": "2.0", "id": 1, "method": "tools/call",
  "params": {
    "name": "list_models",
    "arguments": {"category": "text-to-image", "max_credits": 2}
  }
}

Find image models within 2 credits. Send this tools/call request in a connected MCP session; discovery does not start a paid generation.

02 / LIVE CATALOG PLAYGROUND

Find a model. Build your tool call.

Live catalog · refreshed every five minutes · no account required

Loading the public catalog…

Choose a category and a budget, or inspect a model above. Send the request below to see the live catalog response.

This is live, read-only discovery. Browsing and copying requests do not start a generation.

To generate, sign in with Google and create a token in Account → Agentic AI.

Public catalog request
GET /api/public/models?limit=6&offset=0
No account required · no credits spent
Use these filters in an MCP client
MCP tool call
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "list_models",
    "arguments": {
      "compact": true,
      "limit": 6,
      "offset": 0
    }
  }
}

The public request returns catalog summaries. Authenticated list_models also provides full model parameters and defaults.

Response

Send the request to see the live JSON response here.
View public catalog JSON ↗

PAY AS YOU CREATE

Your next idea doesn’t need another subscription.

Buy credits when you need them. Choose your pack, then spend them on the work you want to make.

Loading current credit packs…

Credits are a balance, not a fixed number of images. Each generation uses credits according to its model, settings and inputs. Browse current model estimates before choosing what to make. Google sign-in is required to purchase and generate.

See what different models cost →

BEFORE YOUR FIRST IDEA

A few things
worth knowing.

Do I need to know how to code?

No. Use the browser workspace to generate images, refine them in chat and work with video. MCP is the additional route for people who want their AI agent to call generation tools.

Can I start without a reference photo?

Yes. Start with a text prompt. Reference images are optional in Image Chat and useful when you want to guide a person, product or scene. Individual MCP models may require specific file inputs.

Where do I make music and speech?

Connect your agent to the MCP server to explore music, speech and other audio models. The live catalog lists the available categories and model requirements.

What do I need to connect my agent?

Sign in with Google, open Account → Agentic AI, and create a bearer token. Save it when it appears: it is shown only once. Add the MCP client config above to a compatible client.

How many images will a credit pack make?

There is no single conversion from credits to images. Cost depends on the model, settings and inputs. The live catalog labels default estimates, input-dependent estimates and output-duration ceilings.

Is there a monthly subscription?

No. Buy a credit pack when you need more. Credits remain available as long as your account stays active; see the Terms of Service for the full conditions.

START WITH THE IDEA YOU ALREADY HAVE

You’ve pictured it.
Now make a first version.

A new image. A scene in motion. A workflow your agent can run. Start with one thing you want to create.

Sign in with Google · No subscription