Skip to main content

Research · Technical

Adding Conditional Control to Text-to-Image Diffusion Models (ControlNet)

IEEE/CVF International Conference on Computer Vision (ICCV 2023) · Zhang, L., Rao, A., Agrawala, M. · Oct 2023

Key points

  1. Adds spatial conditioning such as pose, depth and edges to pretrained text to image diffusion models.
  2. Enables pose controlled character generation, now core to AI character design teaching.
  3. Among the most cited creative AI papers, with over 5,000 citations.

Summary

ControlNet introduces a neural network architecture that adds spatial conditioning inputs (pose skeletons, depth maps, edge maps, and other structural signals) to pretrained text-to-image diffusion models without requiring full retraining. The result is controllable image generation where the spatial layout and character pose can be specified precisely, a capability that has become foundational in AI character design workflows. With over 5,000 citations, ControlNet is a landmark of the generative image field and appears in virtually every node-based workflow taught in animation and concept art courses today.

Source

Source: IEEE/CVF International Conference on Computer Vision (ICCV 2023) ↗ (Research)

Cite this item

Zhang, L., Rao, A. & Agrawala, M. (2023). ‘Adding Conditional Control to Text-to-Image Diffusion Models (ControlNet)’, IEEE/CVF International Conference on Computer Vision (ICCV 2023). Available at: https://openaccess.thecvf.com/content/ICCV2023/html/Zhang_Adding_Conditional_Control_to_Text-to-Image_Diffusion_Models_ICCV_2023_paper.html

Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.