For the complete documentation index, see llms.txt. This page is also available as Markdown.

FLORA MCP recipes

Step-by-step FLORA MCP recipes for common jobs: generate, animate, batch, run Techniques, upload files, arrange the canvas, iterate and brief your agent.

Each recipe is one job you can hand to your agent once FLORA MCP is connected. It gives you a prompt to copy, then the exact flora_* tool calls the agent makes, so you know what to expect and an agent can follow it step by step. Not connected yet? Start with the quickstart.

Find a recipe by job

I want to…
Recipe
Key tools

Make a few images, a video, 3D, audio or text

flora_list_models, flora_create_generations, flora_list_generations

Animate a product photo

flora_create_generations, or flora_add_to_canvas + flora_run_canvas_nodes

Make one asset per row of a list (20 to 500)

flora_create_generations (20 per call), flora_list_generations

Run a saved workflow my team built

flora_list_techniques, flora_get_technique, flora_run_technique

Use my own images, video, audio or PDFs

flora_create_asset (with project_id), flora_complete_asset

Lay results out as a grid or a board

flora_arrange_canvas, flora_add_to_canvas, flora_organize_canvas_fields

Get more like the ones I liked

flora_create_generations with reference_node_ids

Get better results from my agent

(any)

Choosing between neighbours

  • Generate, batch or Technique? Use generate for up to 20 one-off items in a single call. Use batch when the input is a list and every row gets the same style; it adds quoting the whole batch, chunking, and retrying only failures. Use a Technique when your team has already saved the steps, prompts and models; for a list, run one Technique per row with the batch method.

  • Generate or image to video? A video from a prompt alone is generate. A video that starts from a photo is image to video.

  • Iterate or generate again? If the new images should look like earlier ones, iterate passes the earlier outputs as references. Generating again from the same prompt only re-rolls.

Rules every recipe follows

Polling rule. Save every run_id. Wait at least 15 seconds between polls, or 2 seconds per run for bigger batches (40 seconds for 20 runs). Then read every run_id in one flora_list_generations call (up to 20 per call). For example: flora_list_generations({"run_ids": ["run_a", "run_b"]}). For Technique runs, also pass "technique_id". Polling faster returns 429 or cooldown errors with retry_after_seconds.

The details behind these rules are in FLORA MCP cost, balance and limits and FLORA MCP runs: polling, timeouts and failures. Every tool and argument is in the tools reference, and the skills package many of these recipes as instructions your agent can load.

Last updated

Was this helpful?