Step by step 4 steps

1. 1

   Step 1 of 4

   Install the Higgsfield CLI

   Go to higgsfield.ai/cli. Higgsfield gives you three setup commands.

   

   Run them in a fresh project folder:

   Copy

   npm install -g @higgsfield/cli
   higgsfield auth login
   npx skills add higgsfield-ai/skills

   The second command opens a browser so you can sign in with your Higgsfield account. A free account works for testing. Paid plans and extra credits are useful once you start generating more assets.

   When you run the skills command, choose Claude Code when prompted. You can install the skill for the current project or globally. For a first test, project-level install is cleaner because it keeps the experiment contained.

   Pro tip: if setup gets confusing, ask Claude Code to help you install it. It can check whether Node and npm are installed, run higgsfield --help, and explain any terminal errors.

2. 2

   Step 2 of 4

   Ask Claude Code to Inspect Higgsfield

   Once the CLI is installed, open Claude Code in the same folder.

   Ask it to inspect the Higgsfield CLI page and the local command:

   Copy

   Look at https://higgsfield.ai/cli and inspect the local Higgsfield CLI.
   Confirm the install worked, show me the command pattern, and list the available image models.
   Do not generate anything yet.

   Claude Code should check the CLI before spending credits.

   

   This is where the workflow starts to click. Claude Code can see the Higgsfield command, understand the available model names, and decide which model IDs to use in later commands.

   If Claude Code lists video models too, tighten the instruction and tell it to use image models only for this test.

   

3. 3

   Step 3 of 4

   Run One Prompt Through Six Models

   Now give Claude Code one image prompt and ask it to run a real comparison.

   Use this prompt:

   Copy

   Use the Higgsfield CLI to generate this prompt with six different image models:
   
   "A retro 1970s travel photo of Mount Fuji at sunrise, soft film grain, warm colors, vintage postcard composition."
   
   Create a `higgsfield-model-test` folder.
   Save each output with the model name.
   Create `comparison.md` with the model, command, output file, and quick notes.
   Use image models only.
   Download the final image files locally when each generation finishes.

   That last line matters. In testing, the first generation returned a hosted image link. If that happens, just tell Claude Code to download the image when it is done.

   

   The useful part is not just that Higgsfield can generate an image. The useful part is that Claude Code can run the commands, wait for results, save files, and keep the comparison organized.

   

   Use the saved outputs to compare framing, texture, color, and realism across models before choosing a direction.

4. 4

   Step 4 of 4

   Pick a Winner and Iterate

   After the six images are saved, ask Claude Code to review the folder and summarize the differences.

   Use a prompt like this:

   Copy

   Review the images in `higgsfield-model-test`.
   Update `comparison.md` with:
   - the strongest image overall
   - the best image for social
   - the best image for a newsletter hero
   - what each model did well
   - what prompt change we should try next

   Then run one more focused pass. For example, if one model nailed the color but another handled composition better, ask Claude Code to combine those notes into a tighter prompt and test two or three finalists.

   You can also use this as a cost-control workflow. Test rough concepts on cheaper models first, then send the strongest prompt to a higher-quality model once the direction is clear.

Background and context

Who This Is Useful For

• Content creators who want to test a visual idea across several AI image models
• Marketers who need fast campaign concepts, thumbnails, product shots, or social images
• Claude Code users who prefer running creative workflows from the terminal
• AI power users who want one agent to generate, download, name, and organize outputs

What You Will Build

You will set up the Higgsfield CLI, connect it to Claude Code, and run one image idea through six different image models.

The finished output is a small local folder with generated images named by model, plus a simple comparison file you can use to pick the best direction.

What You Need

• Claude Code
• A Higgsfield account, free or paid
• Node/npm installed
• A terminal
• One image prompt you want to test

You can run this directly in your terminal or from the Claude Code desktop app. The recording used Claude Code and the Higgsfield CLI because the MCP path had authentication friction, while the CLI worked right away.

Going Further

• Add this setup to OpenClaw or Hermes Agent.
• Try the same model-comparison workflow with short clips using Higgsfield video generation.
• Use Claude Code as the operator, Higgsfield as the creative engine, and your terminal as the place where prompts turn into organized content assets.