Weavy: Multi-model video generation pipeline

Weavy Try it →Watch full video →Machine Cinema · Nov 2025

Demo summary

A demonstration of a video workflow that takes an image and a system prompt to trigger simultaneous video generation across Kling, V3, and SeaArt models.

Step-by-step

Paste your custom GPT instructions or system prompt into the designated text box
Upload or drop in the image you want to animate
Enter your specific shot request or prompt
Lock the system prompt box if you do not intend to iterate on the core instructions
Click the 'Go' button to trigger simultaneous generation across multiple models

Options

Edit or iterate on the system prompt to change the cinematic style
Generate across specific models including Kling, V3 2.5, Miniac, CyDance, and SeaArt

Watch out for

Running a multi-model generation requires a significant amount of credits (e.g., 400 credits for one run)

Tips

Lock the system prompt once you are satisfied with it to avoid accidental changes
Use a system prompt designed to create vivid cinematic prompts to ensure 'real looking' outputs
If you have a custom GPT you like, ask it for its 'custom instructions' and paste them directly into the tool

Highlights

“Sometimes it feels a little bit confusing, but you know, again, you're only editing this.”

All demos from “RoboDojo w/ Rory Flynn - Weavy.ai Masterclass”

35:372:12Building a batch product ad workflow in WeavyRory 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 pipelineCurrentA 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” →

Image to Video

0:580:49Generating video from image outputs across multiple modelsThe demo shows an array of image models (SDXL, DALL-E, etc.) connected to video models like Runway, Kling, and Luma to generate video from a selected image.Figma Weave
1:07:411:57Multi-model video generation pipelineCurrentA demonstration of a video workflow that takes an image and a system prompt to trigger simultaneous video generation across Kling, V3, and SeaArt models.Machine Cinema