Comfy-agent generate_flux_multi_input_img2img

name: generate_flux_multi_input_img2img description: Generate one image from 2 or 3 already-uploaded Comfy input images using a FLUX multi-reference img2img pipeline. inputs: prompt: type: string description: Main prompt text used for CLIP encoding. images: type: array required: false description: List of 2 or 3 Comfy input filenames from upload_image. image1: type: string required: false description: Comfy input filename from upload_image. image2: type: string required: false description: Comfy input filename from upload_image. image3: type: string required: false description: Comfy input filename from upload_image. outputs: status: type: string run_id: type: string prompt_id: type: string filename_prefix: type: string output_images: type: array artifacts: type: array engine: type: string description: 'Selected backend engine: flux or checkpoint.' requirements: models: [] custom_nodes: [] links: [] input_modalities:

• text_prompt output_modalities:
• application/json model_families:
• other node_count: null node_types: [] selection_metadata: family: img2img_inpaint_outpaint resource_profile: unknown complexity_score: null estimated_runtime: depends on runtime parameters and server resources warnings:
• Hand-authored skill (no embedded workflow.json); metadata is inferred and may be approximate. max_width: null max_height: null max_steps: null