demobook

Higgsfield: Create a location scheme using GPT Image 2

Demo summary

The user demonstrates drawing dots on a location image and using GPT Image 2 to generate a formal production scheme to fix object positioning in video generations.

Step-by-step

  1. Open GPT Image 2
  2. Attach a location image as the input
  3. Prompt for a high angle wide shot of the location
  4. Open the resulting image in any drawing software and draw dots to mark object positions
  5. Return to GPT Image 2 and attach the image with the hand-drawn dots plus a prop sheet
  6. Prompt the AI to place the props where the circles are located and create a location scheme

Options

  • Use any drawing software to manually mark positions

Tips

  • Use this process to help others understand the exact position of every object in a setting
  • Include a prop sheet alongside your marked-up image to ensure the AI identifies the correct objects

Highlights

This is a real location plan

All demos from “I Made a Cinematic Ad Using Claude Fable 5 + Higgsfield (Full Workflow)

  1. 3:350:22Create a product sheet with GPT Image 2.0The user demonstrates how to upload a product image to GPT Image 2.0 and generate a multi-angle product sheet (front, back, and top shots) for visual consistency.Gpt-2AI Product Photography
  2. 13:160:39Manage project elements in Higgsfield CollabThe user shows how to add character sheets, locations, and props as 'Elements' in the Higgsfield interface so they auto-attach when pasting prompts.HiggsfieldAI Animation Generator
  3. 17:390:47Iterative directing and prompt refinement with ClaudeThe user demonstrates 'directing' the AI by telling Claude what was wrong with a previous generation (e.g., character running backwards) to get an updated prompt.ClaudeAI Image Generator
  4. 27:311:08Create a location scheme using GPT Image 2CurrentThe user demonstrates drawing dots on a location image and using GPT Image 2 to generate a formal production scheme to fix object positioning in video generations.HiggsfieldAI Storyboard Generator
  5. Watch “I Made a Cinematic Ad Using Claude Fable 5 + Higgsfield (Full Workflow)” →

AI Storyboard Generator

  1. 27:311:08Create a location scheme using GPT Image 2CurrentThe user demonstrates drawing dots on a location image and using GPT Image 2 to generate a formal production scheme to fix object positioning in video generations.Higgsfield AI
  2. 12:210:57Automate shot list generation with Claude skillsThe user shows how a custom skill takes a single sentence and an image to generate a highly detailed, multi-shot prompt for cinematic video generation.Roboverse
  3. 4:591:00Refine AI video storyboards and character consistencyThe user demonstrates how to use approval gates in Higgsfield to maintain character consistency and modify specific scenes in a storyboard before final video generation.Zinho Automates
  4. 0:500:20Generate story nodes with Higgsfield CanvasThe user inputs a prompt into Higgsfield's canvas agent to generate a node structure for images and video shots, though the demonstration notes a lack of continuity between assets.Joseph Martin