Weavy: Extracting camera angles using LLM nodes
Weavy
Demo summary
The 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.
Step-by-step
- Search for and drag a resizing node from the node library into the workspace
- Connect the 3D model image to the resizer and set dimensions to 265x265
- Add a text node and input a prompt asking the AI to describe the camera angle in one sentence without mentioning the object
- Drag an LLM node (such as ChatGPT) into the workspace
- Connect the text node to the prompt section of the LLM node
- Connect the resized image to the LLM node
- Click Run Model to generate the camera angle description
Options
- Manually type the camera angle description instead of using an LLM node
Tips
- Instruct the AI to describe the angle in maximum one sentence to keep the output concise
- Explicitly tell the AI not to mention the object itself in the description to focus purely on the camera perspective
Highlights
“Awesome. Here is our result. So now it is saying low angle camera looking upward from below which is exactly what is happening over here.”
All demos from “How to Use Weavy AI — Full Guide + Workflow Included (Figma Weave)”
- 0:561:06Basic image generation in Weavy AIThe user demonstrates the basic node-based interface of Weavy AI by connecting a prompt node to a Google Imagen 3 node to generate an image of a dog and cat.Weavy· AI Image Generator
- 3:162:13Building a multi-node image generation workflowThe creator demonstrates building a complex workflow in Weavy AI using prompt concatenators and the Google Imagen 3 model to generate a specific highball glass image.Weavy· AI Image Generator
- 7:341:48Extracting camera angles using LLM nodesCurrentThe 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.Weavy· AI Image Generator
- 9:311:59Controlled image generation with Flux Depth ProThe creator demonstrates using the Flux Depth Pro node to generate a final high-quality image that preserves the spatial orientation and angle of the previously created 3D model.Weavy· AI Image Generator
- 11:501:34Swapping objects in a pre-built AI workflowThe video shows the efficiency of the node system by swapping the 'glass' prompt for a 'banana' prompt to generate a new object in the exact same camera angle using the existing pipeline.Weavy· AI Inpainting
- Watch “How to Use Weavy AI — Full Guide + Workflow Included (Figma Weave)” →
AI Image Generator
- 0:561:06Basic image generation in Weavy AIThe user demonstrates the basic node-based interface of Weavy AI by connecting a prompt node to a Google Imagen 3 node to generate an image of a dog and cat.Artturi Jalli
- 3:162:13Building a multi-node image generation workflowThe creator demonstrates building a complex workflow in Weavy AI using prompt concatenators and the Google Imagen 3 model to generate a specific highball glass image.Artturi Jalli
- 7:341:48Extracting camera angles using LLM nodesCurrentThe 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
- 9:311:59Controlled image generation with Flux Depth ProThe creator demonstrates using the Flux Depth Pro node to generate a final high-quality image that preserves the spatial orientation and angle of the previously created 3D model.Artturi Jalli
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.Machine Cinema- 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.Machine Cinema
- 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.Machine Cinema
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- 21:054:47Build a one-click mood board generatorRory demonstrates a complex Weavy AI workflow that uses Gemini Flash and Flux to batch-process 12 distinct visual prompts from a single image to generate a complete 12-box mood board.Rourke Heath
34:473:06Scaling image generation with prompt arrays in Weavy AIThe 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
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
2:181:57Generate character variations with Flux Pro and Higgsfield in WeavyThe creator demonstrates how to use image generator nodes like Flux Pro and Higgsfield within Weavy, utilizing a text iterator node to run multiple prompts simultaneously for a Cyberpunk character.Sebastian Kamph