chenxwh / ominicontrol-spatial

Minimal and Universal Control for Diffusion Transformer - demo for Spatially aligned control

replicate.com
Total runs: 96
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Github
Model's Last Updated: January 01 2025

Introduction of ominicontrol-spatial

Model Details of ominicontrol-spatial

Readme

OminiControl: Minimal and Universal Control for Diffusion Transformer

This is the demo for Spatially aligned control. See https://replicate.com/chenxwh/ominicontrol-subject for Subject-driven generation.

Features

OminiControl is a minimal yet powerful universal control framework for Diffusion Transformer models like FLUX .

  • Universal Control 🌐 : A unified control framework that supports both subject-driven control and spatial control (such as edge-guided and in-painting generation).

  • Minimal Design 🚀 : Injects control signals while preserving original model structure. Only introduces 0.1% additional parameters to the base model.

Citation
@article{
  tan2024omini,
  title={OminiControl: Minimal and Universal Control for Diffusion Transformer},
  author={Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, and Xinchao Wang},
  journal={arXiv preprint arXiv:2411.15098},
  year={2024}
}

Runs of chenxwh ominicontrol-spatial on replicate.com

96
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About ominicontrol-spatial replicate.com Model

More ominicontrol-spatial license Visit here:

https://github.com/Yuanshi9815/OminiControl/blob/main/LICENSE

ominicontrol-spatial replicate.com

ominicontrol-spatial replicate.com is an AI model on replicate.com that provides ominicontrol-spatial's model effect (Minimal and Universal Control for Diffusion Transformer - demo for Spatially aligned control), which can be used instantly with this chenxwh ominicontrol-spatial model. replicate.com supports a free trial of the ominicontrol-spatial model, and also provides paid use of the ominicontrol-spatial. Support call ominicontrol-spatial model through api, including Node.js, Python, http.

ominicontrol-spatial replicate.com Url

https://replicate.com/chenxwh/ominicontrol-spatial

chenxwh ominicontrol-spatial online free

ominicontrol-spatial replicate.com is an online trial and call api platform, which integrates ominicontrol-spatial's modeling effects, including api services, and provides a free online trial of ominicontrol-spatial, you can try ominicontrol-spatial online for free by clicking the link below.

chenxwh ominicontrol-spatial online free url in replicate.com:

https://replicate.com/chenxwh/ominicontrol-spatial

ominicontrol-spatial install

ominicontrol-spatial is an open source model from GitHub that offers a free installation service, and any user can find ominicontrol-spatial on GitHub to install. At the same time, replicate.com provides the effect of ominicontrol-spatial install, users can directly use ominicontrol-spatial installed effect in replicate.com for debugging and trial. It also supports api for free installation.

ominicontrol-spatial install url in replicate.com:

https://replicate.com/chenxwh/ominicontrol-spatial

ominicontrol-spatial install url in github:

https://github.com/chenxwh/OminiControl

Url of ominicontrol-spatial

ominicontrol-spatial replicate.com Url

ominicontrol-spatial Github

ominicontrol-spatial Owner Github

Provider of ominicontrol-spatial replicate.com

Other API from chenxwh

replicate

Fast sdxl with higher quality

Total runs: 729.7K
Run Growth: 0
Growth Rate: 0.00%
Updated:May 27 2024
replicate

CogVLM2: Visual Language Models for Image and Video Understanding

Total runs: 650.6K
Run Growth: 0
Growth Rate: 0.00%
Updated:September 25 2024
replicate

Depth estimation with faster inference speed, fewer parameters, and higher depth accuracy.

Total runs: 194.7K
Run Growth: 0
Growth Rate: 0.00%
Updated:June 30 2024
replicate

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Total runs: 55.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:May 18 2024
replicate

Audio-based Lip Synchronization for Talking Head Video

Total runs: 28.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 16 2024
replicate

Fast and High-Quality Text-to-video Generation

Total runs: 4.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:June 01 2024
replicate

OmniGen: Unified Image Generation

Total runs: 4.0K
Run Growth: 0
Growth Rate: 0.00%
Updated:November 04 2024
replicate

Scalable Streaming Speech Synthesis with Large Language Models

Total runs: 3.0K
Run Growth: 0
Growth Rate: 0.00%
Updated:December 26 2024
replicate

DiT-based video generation model for generating high-quality videos in real-time

Total runs: 2.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:November 24 2024
replicate

Convert LLM's coding to image generation

Total runs: 1.9K
Run Growth: 0
Growth Rate: 0.00%
Updated:June 03 2024
replicate

Sharp Monocular Metric Depth in Less Than a Second

Total runs: 1.2K
Run Growth: 0
Growth Rate: 0.00%
Updated:October 13 2024
replicate

Minimal and Universal Control for Diffusion Transformer - demo for Subject-driven generation

Total runs: 1.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:January 01 2025
replicate

Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Total runs: 1.1K
Run Growth: 0
Growth Rate: 0.00%
Updated:December 29 2024
replicate

CogVLM2: Visual Language Models for Image and Video Understanding

Total runs: 573
Run Growth: 0
Growth Rate: 0.00%
Updated:September 25 2024
replicate

Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Total runs: 358
Run Growth: 0
Growth Rate: 0.00%
Updated:November 24 2024
replicate

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Total runs: 333
Run Growth: 0
Growth Rate: 0.00%
Updated:May 24 2024
replicate

Extended video synthesis model that generates 128 frames

Total runs: 203
Run Growth: 0
Growth Rate: 0.00%
Updated:July 01 2024
replicate

Depth Any Video with Scalable Synthetic Data

Total runs: 150
Run Growth: 0
Growth Rate: 0.00%
Updated:October 20 2024
replicate

High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Total runs: 147
Run Growth: 0
Growth Rate: 0.00%
Updated:December 07 2024
replicate

Generating Consistent Long Depth Sequences for Open-world Videos

Total runs: 141
Run Growth: 0
Growth Rate: 0.00%
Updated:October 01 2024
replicate

One Diffusion to Generate Them All

Total runs: 135
Run Growth: 0
Growth Rate: 0.00%
Updated:December 31 2024
replicate

Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Total runs: 131
Run Growth: 0
Growth Rate: 0.00%
Updated:October 07 2024
replicate

Efficient Visual Generation with Hybrid Autoregressive Transformer

Total runs: 121
Run Growth: 0
Growth Rate: 0.00%
Updated:October 19 2024
replicate

Image-to-Video Diffusion Models with An Expert Transformer

Total runs: 74
Run Growth: 0
Growth Rate: 0.00%
Updated:September 22 2024
replicate

Finer and Faster Text-to-Image Generation via Relay Diffusion

Total runs: 44
Run Growth: 0
Growth Rate: 0.00%
Updated:October 15 2024
replicate

Text-to-Video Diffusion Models with An Expert Transformer

Total runs: 42
Run Growth: 0
Growth Rate: 0.00%
Updated:September 21 2024
replicate

Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Total runs: 36
Run Growth: 0
Growth Rate: 0.00%
Updated:October 21 2024
replicate

Autoregressive Video Generation without Vector Quantization

Total runs: 32
Run Growth: 0
Growth Rate: 0.00%
Updated:December 27 2024
replicate

Emu3-Gen for image generation

Total runs: 27
Run Growth: 0
Growth Rate: 0.00%
Updated:September 30 2024
replicate

Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

Total runs: 20
Run Growth: 0
Growth Rate: 0.00%
Updated:September 22 2024
replicate

Emu3-Chat for vision-language understanding

Total runs: 18
Run Growth: 0
Growth Rate: 0.00%
Updated:September 30 2024
replicate

Autoregressive Image Generation without Vector Quantization

Total runs: 14
Run Growth: 0
Growth Rate: 0.00%
Updated:December 27 2024
replicate

Let Vision Language Models Reason Step-by-Step

Total runs: 13
Run Growth: 0
Growth Rate: 0.00%
Updated:December 02 2024
replicate

Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design

Total runs: 10
Run Growth: 0
Growth Rate: 0.00%
Updated:October 14 2024
replicate

Text-to-Video Diffusion Models with An Expert Transformer

Total runs: 4
Run Growth: 0
Growth Rate: 0.00%
Updated:September 21 2024