Building a batch product ad workflow in Weavy

Demo summary
Rory demonstrates a Weavy workflow that takes a single product image and a user prompt, uses an LLM to generate 10 unique variations, and outputs them as a batch of marketing assets.
Step-by-step
- Input a reference product image and a user prompt
- Configure the system prompt to request 10 prompts instead of one
- Add custom rules to separate each prompt with a specific character, such as a star
- Use a prompt concatenator to combine the user prompt and system instructions
- Use an array or text iterator to split the combined text into individual prompt nodes
- Switch to App Mode to simplify the interface for end-users
Options
- Include a visual brand profile or style guide in the system prompt to maintain brand consistency
Watch out for
- You must define rules for separating prompts (e.g., using a star) so the system doesn't run all 10 prompts as a single block of text
Tips
- Build for App Mode to hide the 'spaghetti strings' of the workflow and provide a clean interface for clients
- Use a prompt concatenator to easily merge different pieces of text into one box
Highlights
“It's just like you put in an image, you write your prompt, 20 images come out. Like nothing else. You don't have to look at the spaghetti strings.”
All demos from “RoboDojo w/ Rory Flynn - Weavy.ai Masterclass”
35:372:12Building a batch product ad workflow in WeavyCurrentRory demonstrates a Weavy workflow that takes a single product image and a user prompt, uses an LLM to generate 10 unique variations, and outputs them as a batch of marketing assets.Weavy· AI Product Photography
40:391:48Scaling e-commerce assets for BarkBoxA demonstration of a Weavy app that preserves product details while generating infinite environmental variations for a BarkBox product, showing the results in a grid view.Weavy· AI Product Photography
53:261:24Connecting nodes for multi-model generationA step-by-step walkthrough of connecting a prompt node to multiple image generation nodes (like Reev and Flux) to produce simultaneous outputs in Weavy.Weavy· AI Image Generator
55:111:02Aesthetic testing across multiple AI modelsRory shows how to route a single prompt to seven different models (including Ideogram, Mystic, and Higgsfield) to compare visual styles side-by-side.Weavy· AI Image Generator
56:472:24Modular character and prompt engineeringDemonstration of building a modular prompting system where individual text boxes for lighting, composition, and subject are concatenated into a final prompt for generation.Weavy· AI Image Generator
1:07:411:57Multi-model video generation pipelineA demonstration of a video workflow that takes an image and a system prompt to trigger simultaneous video generation across Kling, V3, and SeaArt models.Weavy· Image to Video- Watch “RoboDojo w/ Rory Flynn - Weavy.ai Masterclass” →
AI Product Photography
35:372:12Building a batch product ad workflow in WeavyCurrentRory demonstrates a Weavy workflow that takes a single product image and a user prompt, uses an LLM to generate 10 unique variations, and outputs them as a batch of marketing assets.Machine Cinema
40:391:48Scaling e-commerce assets for BarkBoxA demonstration of a Weavy app that preserves product details while generating infinite environmental variations for a BarkBox product, showing the results in a grid view.Machine Cinema