Turning Prompts into Five Scalable Workflows with Figma Weave | Figma Blog (opens in new tab)

Figma Weave presents AI creation as a scalable, editable workflow rather than a one-off prompt. Its canvas connects AI models and processing nodes so creators can branch, refine, and reuse each step while maintaining control over imagery, video, audio, and 3D output. The article introduces five workflows, beginning with a method for deriving a reusable visual style from multiple reference images.

Figma Weave as a Creative Workflow Canvas

• Figma Weave evolved from Weavy, which Figma acquired to expand its capabilities in:
  • Image and video generation
  • Animation and motion design
  • Audio and 3D creation
  • VFX and professional editing
• Users can chain prompts and AI nodes together, moving from references to finished assets without losing the ability to revise intermediate steps.
• Figma has published more than 20 Community templates covering tasks such as:
  • Turning images into videos
  • Generating 3D models
  • Combining visual references
  • Comparing image-generation models

Why Workflows Are More Scalable Than Single Prompts

• A single prompt produces one interpretation of a style.
• A workflow lets creators independently adjust how strongly each reference influences the result.
• Individual stages can be reshaped, reused, and applied across multiple assets and channels.
• The example brand, Epoch, demonstrates how the system can support a consistent visual identity based on distorted textures and 3D natural forms.

Combining Two Images into a Reusable Style Guide

• The first workflow combines a hibiscus flower and a rock face from Epoch’s existing visual references.
• Each image is processed through an Image Describer node, which extracts attributes such as:
  • Texture
  • Color
  • Lighting
  • Composition
• The resulting text descriptions can be edited and merged into a new style definition.
• The balance between the two references can be adjusted until the desired blend is achieved.
• The combined style can then be tested across different image-generation models, helping the team validate the look at scale.
• The output is treated as a reusable style system rather than a single prompt for one image.

The practical recommendation is to build visual direction as a modular workflow: analyze existing references, combine and tune their characteristics, and preserve the resulting style definition for reuse in future assets.