<p>This workflow is a creative playground that lets you fuse multiple images and their AI-generated captions into entirely new prompts, which are then used to produce hybrid artworks. It combines Florence captioning, style encoding, and an Ollama-powered prompt fusion system to merge visual and textual descriptions into innovative outputs. Thanks to a recent redesign using ComfyUI’s subgraph feature, the workflow has been simplified into modular building blocks—making it easier to experiment with mixing styles, concepts, and ideas. The result is not a rigid production tool, but more of a playful experiment in blending imagery and imagination.</p>

Flux Krea + Redux Ollama Image Prompt Mixer

<p>Unpacked Florence 2 Nodes from Subgraphs, since it was buggy as hell after importing.</p>

Files with SHA256: 0abb7987df10045949caa641cbad26c76ce6b25172b2e3019af7d9a79a84e0ef