Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
hub Mixed citations
Adding Conditional Control to Text-to-Image Diffusion Models
Mixed citation behavior. Most common role is background (60%).
26
Pith papers citing it
Background
60% of classified citations
abstract
We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.
hub tools
citation-role summary
background 6
method 4
citation-polarity summary
representative citing papers
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.
Factored Classifier-Free Guidance enables per-attribute control in classifier-free guidance for diffusion models to produce more sound counterfactuals.
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.
A multi-teacher distillation framework that packs 50 effect LoRAs and fast sampling into a single adapter while aiming to avoid concept interference.
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
REPA-P aligns intermediate representations in diffusion models with physical states using first-principles PDE residuals to accelerate convergence and boost out-of-distribution robustness on PDE tasks.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
PhysEdit introduces adaptive reasoning depth and spatial masking to make image editing faster and more instruction-aligned without retraining the base model.
GOLD-BEV learns dense BEV semantic maps including dynamic agents from ego-centric sensors by using synchronized aerial imagery for training supervision and pseudo-label generation.
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
CamCo equips image-to-video generators with Plücker-coordinate camera inputs and epipolar attention to improve 3D consistency and camera controllability.
IP-Adapter adds effective image prompting to text-to-image diffusion models using a lightweight decoupled cross-attention adapter that works alongside text prompts and other controls.
SDXL improves upon prior Stable Diffusion versions through a larger UNet backbone, dual text encoders, novel conditioning, and a refinement model, producing higher-fidelity images competitive with black-box state-of-the-art generators.
HuggingGPT is an agent system where ChatGPT plans and orchestrates calls to Hugging Face models to solve complex multi-modal AI tasks.
PhyDrawGen is a neuro-symbolic pipeline that extracts typed scene graphs via LLM, converts them to physically constrained PSLGs via deterministic solver, and refines via fine-tuned Qwen-VL, claiming superior performance over GPT-5-image and Gemini models on 1,449 physics problems.
DiffKT3D transfers priors from video diffusion models to 3D radiotherapy dose prediction via modality-specific embeddings and clinically guided RL, reducing voxel MAE from 2.07 to 1.93 and claiming SOTA over the GDP-HMM challenge winner.
Pro-DG extracts a facade's hierarchical layout via inverse procedural modeling and uses the resulting structure to build control maps that guide stable diffusion edits such as floor duplication while preserving local appearance.
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
SOW uses MLLMs and attention to selectively control unidirectional diffusion for pixel-level fidelity and contextual coherence in text-vision-to-image tasks.
citing papers explorer
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
WildDet3D: Scaling Promptable 3D Detection in the Wild
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
-
MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation
MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.
-
Factored Classifier-Free Guidance
Factored Classifier-Free Guidance enables per-attribute control in classifier-free guidance for diffusion models to produce more sound counterfactuals.
-
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
-
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.
-
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
A multi-teacher distillation framework that packs 50 effect LoRAs and fast sampling into a single adapter while aiming to avoid concept interference.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
REPA-P aligns intermediate representations in diffusion models with physical states using first-principles PDE residuals to accelerate convergence and boost out-of-distribution robustness on PDE tasks.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning
PhysEdit introduces adaptive reasoning depth and spatial masking to make image editing faster and more instruction-aligned without retraining the base model.
-
GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes
GOLD-BEV learns dense BEV semantic maps including dynamic agents from ego-centric sensors by using synchronized aerial imagery for training supervision and pseudo-label generation.
-
PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
-
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
-
CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
CamCo equips image-to-video generators with Plücker-coordinate camera inputs and epipolar attention to improve 3D consistency and camera controllability.
-
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
IP-Adapter adds effective image prompting to text-to-image diffusion models using a lightweight decoupled cross-attention adapter that works alongside text prompts and other controls.
-
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
SDXL improves upon prior Stable Diffusion versions through a larger UNet backbone, dual text encoders, novel conditioning, and a refinement model, producing higher-fidelity images competitive with black-box state-of-the-art generators.
-
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
HuggingGPT is an agent system where ChatGPT plans and orchestrates calls to Hugging Face models to solve complex multi-modal AI tasks.
-
PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
PhyDrawGen is a neuro-symbolic pipeline that extracts typed scene graphs via LLM, converts them to physically constrained PSLGs via deterministic solver, and refines via fine-tuned Qwen-VL, claiming superior performance over GPT-5-image and Gemini models on 1,449 physics problems.
-
Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study
DiffKT3D transfers priors from video diffusion models to 3D radiotherapy dose prediction via modality-specific embeddings and clinically guided RL, reducing voxel MAE from 2.07 to 1.93 and claiming SOTA over the GDP-HMM challenge winner.
-
Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation
Pro-DG extracts a facade's hierarchical layout via inverse procedural modeling and uses the resulting structure to build control maps that guide stable diffusion edits such as floor duplication while preserving local appearance.
-
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
-
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
SOW uses MLLMs and attention to selectively control unidirectional diffusion for pixel-level fidelity and contextual coherence in text-vision-to-image tasks.
-
A Real-Calibrated Synthetic-First Data Engine
A data curation pipeline using diffusion-generated synthetic images improves pose estimation when added to real data but underperforms when used without real anchors.
-
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Seedream 4.0 unifies text-to-image synthesis, image editing, and multi-image composition in an efficient diffusion transformer pretrained on billions of pairs and accelerated to 1.8 seconds for 2K output.