DPF / Agentic creative system / MissionKestrel-01
Kestrel-01 rocket venting on a coastal launch pad before dawn

Brief the mission.Ship the launch.

Give your agent the brief. Dream Pixel Forge plans the campaign, generates the assets, and checks every result before launch.

Connect Dream Pixel ForgeSecure. Scalable. Built for flight.
U
User

Build the launch campaign for KESTREL-01. Hard science. No sci-fi.

A
Agent

Flight article, clean-room payload, range operations, and launch film. I’ll keep the mission system consistent.

Status

04 assets / checked against brief

Kestrel-01 heliophysics satellite during clean-room integration
Range operations team monitoring Kestrel-01
Kestrel-01 lifting off at dawn
Campaign output

Consistent system.
Real operations.
Flight-ready creative.

View system

One brief. Flight-ready creative.

Dream Pixel Forge keeps every asset aligned to your mission reality—from hardware and operations to tone, color, and typography.

Intent in. Direction out.

Name the outcome, audience, and constraints. Your agent turns that into a campaign plan before spending a credit.

Satellite integration representing campaign planning grounded in real hardware
Flight article / Payload integration / Asset 01

One visual system, not four lucky shots.

Images and short-form video share the same hardware, light, palette, and editorial direction—because the agent keeps the full brief in view.

Kestrel-01 range operations room
Range operations / Terminal count / Asset 02

Near-misses get fixed before handoff.

Vision validation scores the work against the brief and brand. Obvious misses are regenerated before the campaign comes back to you.

Kestrel-01 launch ignition
Launch film / First motion / Asset 04

A creative system behind every conversation.

01

Fits the agent you already use

Start in ChatGPT, Claude, Codex, or any MCP client. The finished work returns to the same conversation.

02

One system across every asset

Brand profiles, moodboards, and personas become the creative constraints for the entire campaign.

03

Budgeted and validated

Every run has a hard credit cap, and vision checks each result against the brief before delivery.

04

Still and motion, together

Build the image system and its launch film in one run instead of stitching together separate tools.

Let your agent set itself up.

Paste one brief. It installs the CLI, asks you to approve the machine, and learns the workflow on its own.

Paste into Claude, Codex, or ChatGPT
Set yourself up with Dream Pixel Forge so you can generate on-brand images and video for me.

1. Install the CLI: npm install -g dreampixel-cli (or use npx dreampixel-cli). The command it installs is dpf.
2. Run dpf whoami. If no key is configured, ask me to run dpf login in my terminal: it opens my browser to approve this machine. Never ask me to paste an API key into this chat.
3. Run dpf skill install in the project root so you have the full workflow on disk: create a run, plan concepts, generate, validate with vision, and render video in the background.
4. Confirm the connection with dpf tools, then ask me for my first brief.

If you connect over MCP instead of a terminal, the endpoint is https://www.dreampixelforge.com/api/mcp with my API key as an Authorization: Bearer header.

Agentic creation without the mystery.

What is agentic image and video creation?

Instead of typing prompts into a web form, an AI agent runs the whole creative job: it plans concepts, generates images and video, and checks the results, while you approve the brief and review the output. Dream Pixel Forge ships its own creative director agent in the studio, and the CLI and MCP endpoint let you bring your own.

Which agents can I connect to Dream Pixel Forge?

Any MCP client: the Claude desktop app, claude.ai connectors, Claude Code, Codex, and ChatGPT all work. Any terminal-based coding agent can drive the dpf CLI directly, and dpf skill install teaches it the whole workflow in one command. For clients that prefer a local server, dpf mcp serves the same tools over stdio, and Dream Pixel Forge also ships an agent-plugins.org plugin that packages the server and the workflow skill in one folder.

Do I have to manage API keys?

No. dpf login opens your browser so you can approve the machine: nothing to copy or paste. Headless environments and CI read the DPF_API_KEY environment variable instead, and connectors that cannot send headers can carry the key in the endpoint URL path.

How does my agent stay on brand?

The endpoint serves your brand profile, moodboards, and AI personas to the agent as context. Output matches your style without re-describing it in every request, the same way the built-in creative director works.

What does agentic generation cost?

Generations spend the same credits as any other studio work, and every run carries a 20-credit image budget so an over-eager agent cannot run up your bill. See the pricing page for current credit packs and plans.

Can my agent create video too?

Yes. dpf video renders clips in the background from the same run, and the agent polls dpf run status with the watch flag until the URL is ready. Video works over MCP as well.

Does the agent check its own work?

Yes. dpf vision in validate mode scores a generation against the brief and your brand profile, so the agent fixes near-misses before you ever see them. You review finished results, not raw attempts.

From the blog

Agentic image generation guides: MCP, CLI, and the API behind them.

Your next campaign starts in one sentence.

Approve the connection once, then hand every visual brief to the agent you already trust.

Connect Dream Pixel Forge See pricing