Figma: Scaling image generation with prompt arrays in Weavy AI
FigmaDemo summary
The demo shows how to use an LLM node to generate 10 unique prompt variations from a single idea, splitting them via an array node to produce batch outputs in Weavy AI's app mode.
Step-by-step
- Input a reference image and a user prompt into the system
- Configure the system prompt to request 10 prompt variations instead of one
- Add a rule to separate each generated prompt with a specific character, such as a star
- Use a prompt concatenator to combine text inputs into a single box
- Connect the output to an array node to split the text into individual prompts
- Use a list selector or text iterator to branch the prompts into individual generation nodes
- Switch to App Mode to simplify the interface for end users
Options
- Include a visual brand profile in the system prompt to maintain brand style
- Scale the output from 10 images to 40, 100, or 400 images
Watch out for
- You must include specific separation rules (like a star) in the system prompt or the system will run all 10 prompts as a single block of text
Tips
- Use App Mode when delivering to clients so they only see the input and output without the 'spaghetti strings' of the backend
- Guide the process at each individual step to maintain control over the AI output
Highlights
“Just hit enter and go and that's what comes out.”
All demos from “RoboDojo w Rory Flynn Weavy ai Masterclass 1”
- 34:473:06Scaling image generation with prompt arrays in Weavy AICurrentThe demo shows how to use an LLM node to generate 10 unique prompt variations from a single idea, splitting them via an array node to produce batch outputs in Weavy AI's app mode.Figma· AI Image Generator
- 40:222:16Batch processing product assets for BarkBoxA demonstration of a completed Weavy AI workflow that preserves product details while generating hundreds of background and lighting variations for marketing assets.Figma· AI Product Photography
- Watch “RoboDojo w Rory Flynn Weavy ai Masterclass 1” →
AI Image Generator
29:034:45Automating Multi-Angle Prompts with Array and List NodesThe demonstration shows how to use an 'Array' node to split a single block of text (separated by asterisks) into individual camera angle prompts and then mapping them to a 'List' node for batch processing.DGI Kaos
0:210:17Building node-based AI workflows in Figma WeaveThe video demonstrates the Figma Weave interface where a user connects various AI model nodes and image processing blocks to create a repeatable design machine.Figma Weave
7:341:48Extracting camera angles using LLM nodesThe user demonstrates resizing a 3D model view and using a ChatGPT node to describe the specific camera angle in text for use in further image generation.Artturi Jalli
13:492:32Design a YouTube thumbnail with Weavy AIRory Flynn shows how he uses Weavy AI's compositor node and layers to isolate characters, remove backgrounds, and adjust camera angles to create a consistent aesthetic for a podcast thumbnail.Rourke Heath- 34:473:06Scaling image generation with prompt arrays in Weavy AICurrentThe demo shows how to use an LLM node to generate 10 unique prompt variations from a single idea, splitting them via an array node to produce batch outputs in Weavy AI's app mode.Anderson Edjéme