Research map / Image generation / Text-to-image diffusion
AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation
Yanan Sun, Yanchen Liu, Yinhao Tang, Wenjie Pei, Kai Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train with synthetic unaligned (occluded) multi-control data (ablation) | AnyControl · COCO-UM | FID: 52.10 -> 44.28 FID; CLIP 25.62 -> 26.40 | Improved |
| add more levels of visual tokens from the visual encoder (ablation) | Multi-Control Encoder · COCO-UM | FID: 45.64 -> 43.67 (4 levels); 44.28 (6 levels) | Improved |
| learn composition weights with attention-based Multi-Control Encoder instead of hand-crafted MoE weights | multi-control synthesis · COCO-UM | FID: 55.95 -> 44.28 vs Multi-ControlNet | Improved |
| use AnyControl instead of single-control ControlNet for depth fidelity | COCO-5K depth control · COCO-5K | RMSE: 13.86 -> 15.48 | Hurt |
| use AnyControl for edge control against Cocktail | COCO-5K edge control · COCO-5K | FID: 15.70 -> 18.89 | Hurt |
| increase number of spatial conditions to eight | AnyControl · qualitative | blending quality | Hurt |
Later papers that compared with this method
3 later accepted papers report AnyControl as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation (ICLR 2026 · better on 8 of 8 shared results)
- FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation (CVPR 2025 · better on 4 of 4 shared results)
- VODiff: Controlling Object Visibility Order in Text-to-Image Generation (CVPR 2025 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 5 on most shared results.
- ControlNet — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 1 of 2 shared results
- Uni-ControlNet — Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models (NeurIPS 2023) · better on 1 of 2 shared results
- Cocktail — Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation (NeurIPS 2023) · better on 1 of 2 shared results
- UniControl — UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild (NeurIPS 2023) · better on 2 of 2 shared results
- T2I-Adapter — T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models (AAAI 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition (CVPR 2024 · similarity 0.89)
- Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance (NeurIPS 2024 · similarity 0.88)
- VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis (AAAI 2025 · similarity 0.88)
- FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation (ICML 2025 · similarity 0.88)
- Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation (ICLR 2025 · similarity 0.87)
- CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
