Visual Workflow Builder
Drag, connect, run. Build node-based pipelines that take an idea, enhance the prompt, generate variations, animate the best, and ship to gallery, all in one click. Then re-run with new inputs forever.
Product → Variations → Best → Animation → Gallery. One graph, infinite reuse.
Build it once. Run it on every new product photo with one click.
Nodes
Bring an existing image into the workflow. Reference photo, brand asset, customer screenshot.
A prompt or instruction. Can be templated with variables that change per run.
Run GPT-4o vision over an image to extract colors, demographics, mood, and ad-relevant attributes.
Auto-upgrade a rough idea into a production-grade prompt with style, lighting, and composition cues.
Pick a model (Nano Banana 2, Imagen 4, Flux), set count, get back a batch of variations.
Score generated images on prompt adherence and quality. Filter the top N before downstream nodes consume them.
Animate the chosen image with Kling, Luma, or Veo 3. Aspect ratio, duration, and motion prompt as inputs.
Persist outputs to your gallery, optionally tagged with a collection name and metadata.
CSV of new SKUs in, gallery of finished product imagery and 5-second animations out. Same workflow every Monday.
One reference creative, 20 variants across angle, model, and aspect ratio. Test what wins, then iterate the winning branch.
Brand voice in a Text Input node, fresh imagery generated and saved every day. Schedule with the CLI.