pith. sign in

arxiv: 2408.06070 · v3 · pith:3YEA3LU7new · submitted 2024-08-12 · 💻 cs.CV

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

classification 💻 cs.CV
keywords additionalgenerationmethodtrainingvideocontrolefficientimage
0
0 comments X
read the original abstract

Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development

    cs.CV 2026-06 unverdicted novelty 7.0

    A synthetic patient-free pipeline generates saccadic eye movement data to train a classifier achieving AUROC 0.76 and sensitivity 0.71 on real clinical data for normal vs abnormal saccade detection.

  2. Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework

    cs.CV 2026-04 unverdicted novelty 7.0

    TexADiff integrates a Relative Texture Density Map into diffusion-based super-resolution to address imbalanced textures in remote sensing images, yielding better high-frequency details and downstream task gains.

  3. Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    Immune2V immunizes images against dual-stream I2V generation by enforcing temporally balanced latent divergence and aligning generative features to a precomputed collapse trajectory, yielding stronger persistent degra...

  4. GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling

    cs.CV 2026-02 unverdicted novelty 7.0

    GT-SVJ turns video generative models into self-supervised reward judges via EBM reformulation and contrastive training on controlled synthetic degradations, claiming SOTA on GenAI-Bench and MonteBench with 30K annotations.

  5. One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

    cs.CV 2025-11 unverdicted novelty 7.0

    One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and t...

  6. Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing

    cs.CV 2025-09 unverdicted novelty 7.0

    Vid-Freeze immunizes images by adding perturbations that target attention dynamics in I2V models to enforce temporal freezing and suppress motion synthesis.

  7. PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models

    cs.CV 2025-05 unverdicted novelty 7.0

    PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.

  8. InstanceControl: Controllable Complex Image Generation without Instance Labeling

    cs.CV 2026-06 unverdicted novelty 6.0

    InstanceControl uses VLMs to auto-generate instance masks from text and visual conditions, with adaptive refinement, to enable controllable multi-object image generation without manual labeling.

  9. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

    cs.CV 2026-06 unverdicted novelty 6.0

    Presents a scene-adaptive 3D human animation method using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human trajectories and camera views, reporting gains on two benchmarks.

  10. Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces mesh tokenization to condition DiT-based video diffusion models directly on 3D human meshes for motion control without 2D rendering.

  11. SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages

    cs.CV 2026-05 unverdicted novelty 6.0

    SignVerse-2M provides a 2-million-clip multilingual pose-native dataset for sign language derived from public videos via DWPose preprocessing to enable robust modeling in real-world conditions.

  12. HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis

    cs.CV 2026-03 unverdicted novelty 6.0

    HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on t...

  13. VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification

    cs.CV 2025-12 unverdicted novelty 6.0

    VHOI densifies sparse trajectories into color-encoded HOI mask sequences and conditions a fine-tuned video diffusion model on them to produce controllable human-object interaction videos, including full navigation sequences.

  14. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

    cs.CV 2026-06 unverdicted novelty 5.0

    Presents a scene-adaptive 3D human image animation framework using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human and camera trajectories, claiming improvements on two benchmarks.

  15. LISA: Likelihood Score Alignment for Visual-condition Controllable Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    LISA adds a likelihood-score alignment loss to the side branch of dual-branch controllable generators, accelerating convergence and improving results across image/video tasks with negligible extra cost.

  16. EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.

  17. DepthPilot: From Controllability to Interpretability in Colonoscopy Video Generation

    cs.CV 2026-04 unverdicted novelty 5.0

    DepthPilot generates physically consistent and clinically interpretable colonoscopy videos by injecting depth priors into diffusion models through parameter-efficient fine-tuning and replacing linear denoising weights...

  18. ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation

    cs.RO 2025-09 unverdicted novelty 5.0

    ROPA augments bimanual imitation learning datasets by generating synthetic RGB-D observations and actions via fine-tuned diffusion models with physical consistency constraints.

  19. Open-Sora Plan: Open-Source Large Video Generation Model

    cs.CV 2024-11 unverdicted novelty 4.0

    Open-Sora Plan presents an open-source large video generation model that combines a Wavelet-Flow VAE, Joint Image-Video Skiparse Denoiser, and multi-dimensional data curation to achieve high-quality video outputs with...