1
Open Claude settings
Launch the app or open claude.ai and go to
Turn
Claudeinto a creative engine
Connect Higgsfield to Claude, OpenClaw, Hermes, NemoClaw and generate cinematic images and videos right from your conversations.
2
Add a custom connector
Name it Higgsfield and paste the URL:
3
Connect and sign in
Click Add -> Connect, sign in with your Higgsfield account - you're all set, now just ask Claude to generate an image.
A COMPLETE CREATIVE STUDIO INSIDE CLAUDE
Image generation, video creation, character training, and asset management in a single connection
Generative media
Image & Video Generation
From static stills to full cinematic video - choose your model, set the parameters, and generate. Soul and Nano Banana for images. Seedance, Kling, Veo for video. Up to 4K, any aspect ratio, any duration.
Generative media
Image & Video Generation
From static stills to full cinematic video - choose your model, set the parameters, and generate. Soul and Nano Banana for images. Seedance, Kling, Veo for video. Up to 4K, any aspect ratio, any duration.
Ad engine
One prompt replaces your entire agency
Finds top-spending niches, generates videos across formats UGC, TV spot, Wild Card - writes outreach, and delivers a weekly report. Replaces a $5K/mo retainer - from one brief.
Ad engine
One prompt replaces your entire agency
Finds top-spending niches, generates videos across formats UGC, TV spot, Wild Card - writes outreach, and delivers a weekly report. Replaces a $5K/mo retainer - from one brief.
Brand builder
From zero to a profitable brand
Finds an underserved product, sources a factory, generates listing photos and hero video, mines reviews for counter-narrative ads, builds the D2C site.
Brand builder
From zero to a profitable brand
Finds an underserved product, sources a factory, generates listing photos and hero video, mines reviews for counter-narrative ads, builds the D2C site.
Content at scale
Automated content for any niche
Pulls listings or trends, generates a polished video per item, and distributes via WhatsApp, YouTube, or wherever your audience is. Whole channel on autopilot - zero agency fees.
Content at scale
Automated content for any niche
Pulls listings or trends, generates a polished video per item, and distributes via WhatsApp, YouTube, or wherever your audience is. Whole channel on autopilot - zero agency fees.
Presets
Pick a format, skip the setup
Query 9 curated video presets - UGC, unboxing, product review, hyper motion, TV spot, and more - and pass the right mode into generation automatically
Presets
Pick a format, skip the setup
Query 9 curated video presets - UGC, unboxing, product review, hyper motion, TV spot, and more - and pass the right mode into generation automatically
FROM CONCEPT TO CONTENT IN ONE CONVERSATION
Tell Claude what you're working on. It picks the right models and delivers production-ready results
From idea to campaign in one conversation
Start small with a quick generation, or go deep with multi-model comparisons, character training, and full campaign workflows. Claude handles the complexity
Asset Creation
Generate one asset in seconds
Describe what you need and Claude picks the best model, sets the parameters, and delivers the result. Images, videos, or both.
Generate a cinematic wide shot of a neon-lit Tokyo alley at night
Full Production
Build a visual system from a conversation
Train a character, generate scenes across locations and styles, produce videos, and manage everything from your generation history.
Train a Soul Character from these photos, then generate a 10-image lookbook
Multi-Model
Compare the best AI models side by side
Run the same prompt through Flux, Soul, Cinema Studio, and Seedream in one go. Pick the winner and iterate from there.
Generate this scene on 4 different models and show me the results
Got any questions left?
We’ve answered the most frequently asked questions
How does Higgsfield connect to AI agents?
Higgsfield uses MCP (Model Context Protocol), an open standard that gives AI agents access to external tools. Once connected, your agent can generate images, create videos, train characters, and browse your creation history, all within a single session.
Which agents are supported?
Higgsfield MCP works with Claude (web, Cowork, and Claude Code), OpenClaw, Hermes Agent, and NemoClaw. Any agent or client that supports MCP can connect to Higgsfield.
What models are available?
Higgsfield gives your agent access to 30+ models including Soul, Cinema Studio, Flux, Seedream, Kling, Minimax Hailuo, Veo, and more. Your agent automatically selects the best model for the task, or you can specify one yourself.
What can I create?
Images up to 4K resolution, videos up to 15 seconds across multiple cinematic styles, consistent characters using Soul training, and more. You can generate from text prompts, reference images, or a combination of both.
Do I need an API key?
No. Add the Higgsfield MCP server URL in your agent's settings and authenticate through your Higgsfield account. No API keys to manage or configure.
How does pricing work?
Higgsfield tools use the same credit system as the Higgsfield platform. Each generation costs credits based on the model and resolution. Your existing Higgsfield plan credits work seamlessly through any connected agent.
How long does generation take?
Images typically complete in a few seconds. Videos take longer depending on duration and model. All generation runs asynchronously, so your agent polls for results and delivers them as soon as they're ready.
Can I use previous generations as input?
Yes. You can browse your full generation history, reference any past image or video, and use it as a starting point for new creations. This makes iterative workflows and multi-step production easy.
Can I use Higgsfield with my own agent setup?
Yes. Any MCP-compatible client can connect. If you're running OpenClaw on a VPS, Hermes Agent on your local machine, or NemoClaw on NVIDIA hardware, just point it to the Higgsfield MCP server and you're ready to generate.
YOUR AI STACK JUST LEVELED UP
Connect Claude, OpenClaw, Hermes, or NemoClaw to Higgsfield in seconds. Videos, images, characters — on demand.