Edit an existing image and place the result directly on a user's Avocado AI flow (the Flows Director). This is the flow-native edit: use it (NOT the plain edit_image) for ANY edit inside a flow, so the result lands in the user's Director Library. This MODIFIES ONE SPECIFIC existing image (file_id/image_url is required) — it does not generate new frames from a prompt. To generate a NEW image guided by one or more reference images (e.g. a storyboard beat that must keep the same cast/location consistent), use generate_image_to_flow with reference_image_urls instead. Drops a 'Generating...' tile immediately, then swaps in the edited image when ready (10-60s). REQUIRED: exactly one of file_id OR image_url (HTTPS). For chat-attached images call prepare_image_upload first, then pass the returned file_id. Models: 'nano-banana-2' (fast, default, 1 credit), 'nano-banana-2-lite' (fastest/cheapest, single-image touch-ups, 1 credit), and 'gpt-image-2' (higher quality, 1-4 credits by quality). To regenerate/retouch an EXISTING tile in place (same tile stays 'the' cast/location/beat reference — nothing downstream breaks) instead of creating a duplicate, pass replace_node_id (get it from a prior generate_image_to_flow/edit_image_to_flow response's nodeIds, or from list_flow_assets); typically image_url would then be that same tile's own current url.