Krea-2 Depth ControlNet-LoRA

Give it any image and a prompt — it extracts the depth map with Depth-Anything-V2 and generates a new image with the same 3D structure and composition, but whatever content and style you ask for. Powered by Krea-2-Turbo (8-step) + the depth-control LoRA.

Best with photos / renders that have real perspective. Flat 2D illustrations give weak control. Empty prompt = depth-only generation.