Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

Invoker-Render

Invoker-Render is a video-to-video AI model with 33 billion parameters, designed for controllable video generation. It utilizes visual proxies to fix camera paths, scene layouts, and object motions, then generates appearances based on these structural inputs, an appearance reference image, and text prompts. The model supports long-horizon streaming and multi-granularity control for diverse video rendering tasks.

View Model
Share
View Model
Share

Invoker-Render is a sophisticated video-to-video AI model, developed by inclusionAI, that enables highly controllable video generation. With 33.12 billion parameters, this model focuses on generating video appearances based on structural proxies, a single appearance reference image, and textual prompts. It operates on the principle of keeping the world state in an upstream engine, where visual proxies dictate elements like camera path, scene layout, and object motion, while the video model handles the visual rendering.

Read More

The core of Invoker-Render lies in its causal streaming DiT weights, which are hosted in its repository. The model is designed to work in conjunction with the companion CodeWorldModel inference code, facilitating causal four-step streaming generation. This setup is built upon robust frameworks such as MiniMax-H3, SGLang, and SGLang-Omni, ensuring efficient and scalable operation.

Key highlights of Invoker-Render include its capability for long-horizon streaming, which allows sessions to run indefinitely as long as proxy frames are provided. This is achieved through a fixed appearance anchor and a bounded history window, maintaining visual consistency over extended periods. Furthermore, the model offers multi-granularity control, accepting a wide range of structural inputs such as semantic maps, sparse 3D boxes, subject masks, shaded geometry, and boxes with skeletons, providing users with precise control over the generated video content.

For interactive deployment, the companion code provides a WebSocket session service, a file client, and a browser client, making the model accessible for various applications. The model's weights are stored in FP32 format across 29 safetensors shards, totaling approximately 132.5 GB. While the repository includes the main causal streaming DiT weights, users need to prepare matching assets like VAE, Qwen, the causal decoder, and silence tensors separately for inference. The default production profile for inference typically requires eight NVIDIA GPUs on a single node, processing inputs like a 1344×768 RGB first image, a 24 FPS proxy video, and a text prompt.

  • CategoryAI Models & LLMs
  • DeploymentCloud
  • PlatformsWeb

  • Video-to-Video Model: Generates video appearances from structural proxies and inputs.

  • 33 Billion Parameters: Large model size for advanced video generation capabilities.

  • Proxy-Conditioned Rendering: Uses visual proxies to control camera path, scene layout, and object motion.

  • Appearance Reference Image Input: Takes one image to guide the visual style.

  • Text Prompt Input: Accepts textual descriptions for content generation.

  • Causal Streaming DiT Weights: Utilizes specific model weights for streaming generation.

  • Long-Horizon Streaming: Supports continuous video generation as proxy frames arrive.

  • Fixed Appearance Anchor: Maintains consistent appearance over long sessions.

  • Multi-Granularity Control: Accepts diverse structural inputs like semantic maps, 3D boxes, and subject masks.

  • Interactive Deployment: Companion code offers WebSocket, file, and browser clients.

  • FP32 Weights: Model weights stored in full precision.

  • MiniMax-H3 Base Model: Built on the MiniMax-H3 architecture.

  • Apache-2.0 License: Governs the repository's use.

  • CC BY-NC 4.0 License: Applies to non-commercial use.

  1. Access Model Weights: Download the main causal streaming DiT weights from the repository root.

  2. Prepare Assets: Separately acquire and prepare matching assets such as VAE, Qwen, and the causal decoder.

  3. Set Up Environment: Follow the README.md and docs/INFERENCE.md in the companion CodeWorldModel repository.

  4. Prepare Bundle: Create an inference bundle as instructed in the companion repository.

  5. Start Service or Run Inference: Initiate the WebSocket session service or execute file inference using invoker_render.py.

  6. Provide Inputs: Supply a 1344×768 RGB first image, a 24 FPS proxy video, and a text prompt.

  • Controllable Video Generation
  • Long-Form Video Creation
  • Semantic Video Editing
  • 3D Scene Rendering
  • Interactive Video Applications

Invoker-Render Reviews

Loading...

Popular AI Tools Like Invoker-Render

Muse Glimmer

AI Models

Muse Glimmer is a 30-billion-parameter causal language model designed for autonomous agentic tasks on consumer hardware. It integrates multi-step reasoning, reliable tool use, and…

AI Models & LLMs
View Tool

AI Models

30-billion-parameter causal language model designed for autonomous agentic tasks on consumer hardware. It integrates multi-step reasoning, reliable tool use, and…Muse Glimmer is a 30-billion-parameter causal language model designed for autonomous agentic tasks on consumer hardware. It integrates multi-step reasoning, reliable tool use, and…

FeaturedAI Models & LLMs
See the Top 5 AI Models

VideoPoet

AI Models

VideoPoet is a large language model from Google Research capable of zero-shot video generation. It transforms autoregressive language models into high-quality video generators,…

AI Video Generators
View Tool

AI Models

Large language model from Google Research capable of zero-shot video generation. It transforms autoregressive language models into high-quality video generators,…VideoPoet is a large language model from Google Research capable of zero-shot video generation. It transforms autoregressive language models into high-quality video generators,…

AI Video Generators
See the Top 5 AI Models

SenseNova 6.8 Code2Video is a code-driven video creation model that generates executable code to build and render short videos. It connects various models and tools for a complete…

AI Models & LLMs

Ranked #77 in LLMs

View Tool

Code-driven video creation model that generates executable code to build and render short videos. It connects various models and tools for a complete…SenseNova 6.8 Code2Video is a code-driven video creation model that generates executable code to build and render short videos. It connects various models and tools for a complete…

AI Models & LLMs
Ranked #77 in LLMs

Imagen Video

AI Models

Imagen Video is a text-conditional video generation system developed by Google Research. It leverages a cascade of video diffusion models to create high-definition videos from…

AI Video Generators
View Tool

AI Models

Text-conditional video generation system developed by Google Research. It leverages a cascade of video diffusion models to create high-definition videos from…Imagen Video is a text-conditional video generation system developed by Google Research. It leverages a cascade of video diffusion models to create high-definition videos from…

AI Video Generators
See the Top 5 AI Models

Linum P-JiT is an experimental 2B-parameter text-to-image model developed by Linum, a two-person research lab focused on generative video models. This proof-of-concept model…

AI Models & LLMs
View Tool

Experimental 2B-parameter text-to-image model developed by Linum, a two-person research lab focused on generative video models. This proof-of-concept model…Linum P-JiT is an experimental 2B-parameter text-to-image model developed by Linum, a two-person research lab focused on generative video models. This proof-of-concept model…

AI Models & LLMs
See the Top 250 AI Apps

Flux 3 is an AI video generator that creates videos from text, images, or reference clips. It features native audio, natural motion, and multilingual dialogue, allowing users to…

AI Video GeneratorsMedia & Entertainment
View Tool

AI video generator that creates videos from text, images, or reference clips. It features native audio, natural motion, and multilingual dialogue, allowing users to…Flux 3 is an AI video generator that creates videos from text, images, or reference clips. It features native audio, natural motion, and multilingual dialogue, allowing users to…

AI Video GeneratorsMedia & Entertainment
See the Top 250 AI Apps

VideoAI

AI Apps

VideoAI is an AI video generator that turns text and images into videos using leading models such as Kling, Wan, Seedance, and Veo. It also offers image tools and AI music…

AI Video GeneratorsMedia & Entertainment

Ranked #119 for Writing video scripts

View Tool

AI Apps

AI video generator that turns text and images into videos using leading models such as Kling, Wan, Seedance, and Veo. It also offers image tools and AI music…VideoAI is an AI video generator that turns text and images into videos using leading models such as Kling, Wan, Seedance, and Veo. It also offers image tools and AI music…

AI Video GeneratorsMedia & Entertainment
Ranked #119 for Writing video scripts

invideo

AI Apps

invideo is an AI video creation and editing platform built around Agent Two, letting users generate and edit videos with multiple AI models and 5,000+ templates. It serves…

AI Short Video Makers

Ranked #37 in AI Apps

View Tool

AI Apps

AI video creation and editing platform built around Agent Two, letting users generate and edit videos with multiple AI models and 5,000+ templates. It serves…invideo is an AI video creation and editing platform built around Agent Two, letting users generate and edit videos with multiple AI models and 5,000+ templates. It serves…

FeaturedAI Short Video Makers
Ranked #37 in AI Apps
1 of 8