# tencent-hunyuan/hunyuanvideo-1.5 **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/tencent-hunyuan-hunyuanvideo-1-5).** 4,440 stars · 222 forks · Python · other ## Links - GitHub: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5 - Homepage: https://hunyuan.tencent.com/video/zh?tabIndex=0 - awesome-repositories: https://awesome-repositories.com/repository/tencent-hunyuan-hunyuanvideo-1-5.md ## Topics `image-to-video` `text-to-video` `video-generation` ## Description HunyuanVideo-1.5 is a video generation foundation model and text-to-video diffusion framework. It utilizes a latent video diffusion model and a spatio-temporal transformer architecture to generate high-definition video sequences from text descriptions and images. The project enables cinematic camera control for directing pans and tilts and provides image-to-video animation capabilities. It supports visual style adaptation through low-rank adaptation tuning and uses a language model for prompt refinement to improve visual alignment. The model covers high-resolution video upscaling via a super-resolution network, in-video text rendering, and the manipulation of lighting and mood. It also includes inference acceleration through step distillation to reduce generation time. ## Tags ### Artificial Intelligence & ML - [Text-to-Video Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-video-generators.md) — Generates high-definition video sequences from text descriptions using a latent diffusion model. - [Video Diffusion Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-models/latent-diffusion-models/video-diffusion-models.md) — Provides the core latent video diffusion model that generates high-definition video sequences from text descriptions. - [Language Model Prompt Rewriters](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-prompt-configurations/prompt-evaluation-tools/prompt-refinement-utilities/language-model-prompt-rewriters.md) — Ships a language model that rewrites short user prompts into detailed descriptions for better video generation alignment. - [Spatio-Temporal Attention](https://awesome-repositories.com/f/artificial-intelligence-ml/attention-mechanisms/spatio-temporal-attention.md) — Uses a spatio-temporal transformer backbone to jointly attend to spatial frames and temporal sequences for video generation. - [Prompt Expansion](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-workflows/text-to-video-generation/prompt-expansion.md) — Enriches short user prompts into detailed descriptions using a large language model for better visual alignment. ([source](https://cdn.jsdelivr.net/gh/tencent-hunyuan/hunyuanvideo-1.5@main/README.md)) - [Image-to-Video Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/video-generation/image-to-video-generation.md) — Animates uploaded images by generating subsequent frames based on a text prompt describing motion. - [Generative Lighting Control](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/image-augmentation/lighting-adjusters/generative-lighting-control.md) — Sets the mood of a video by describing lighting style, direction, quality, and color temperature in the prompt. ([source](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/assets/HunyuanVideo_1_5_Prompt_Handbook_EN.md)) - [Style Adaptation](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-ai-models/style-adaptation.md) — Adapts the base model to new visual styles by training low-rank adaptation weight matrices. - [Step-Distilled Accelerators](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/diffusion-models/inference-acceleration/step-distilled-accelerators.md) — Reduces video generation time through step distillation, cache inference, and sparse attention techniques. - [Step-Distilled Accelerators](https://awesome-repositories.com/f/artificial-intelligence-ml/gpu-accelerated-inference/multi-gpu-video-inference-accelerators/step-distilled-accelerators.md) — Accelerates video generation by using step distillation, cache inference, and sparse attention to reduce creation time. ([source](https://cdn.jsdelivr.net/gh/tencent-hunyuan/hunyuanvideo-1.5@main/README.md)) - [Video Super-Resolution Suites](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/video-super-resolution-suites.md) — Ships a dedicated super-resolution network that upscales generated videos to 1080p. ([source](https://cdn.jsdelivr.net/gh/tencent-hunyuan/hunyuanvideo-1.5@main/README.md)) - [In-Video Text Rendering](https://awesome-repositories.com/f/artificial-intelligence-ml/in-video-text-rendering.md) — Generates clear, readable text within video frames by enclosing the desired text in quotation marks. ([source](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/assets/HunyuanVideo_1_5_Prompt_Handbook_EN.md)) - [Inference Acceleration](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-acceleration.md) — Reduces video generation time through step distillation, cache inference, and sparse attention techniques. - [Low-Rank Adaptation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/low-rank-adaptation.md) — Implements low-rank adaptation tuning to adapt the base model to new visual styles by training small weight matrices. - [Step Distillation Accelerators](https://awesome-repositories.com/f/artificial-intelligence-ml/step-based-schedulers/step-execution-engines/execution-step-controllers/denoising-step-controllers/step-distillation-accelerators.md) — Accelerates video generation by distilling the diffusion sampling process into fewer denoising steps. ### Graphics & Multimedia - [Generative Camera Controls](https://awesome-repositories.com/f/graphics-multimedia/generative-camera-controls.md) — Directs camera movements like pans, tilts, and orbits in generated videos through cinematography keywords. - [Generative Video Frameworks](https://awesome-repositories.com/f/graphics-multimedia/video-production/programmatic-video-frameworks/generative-video-frameworks.md) — A framework for creating videos from text and images with camera control, style adaptation, and upscaling. - [Prompt-Based Camera Controls](https://awesome-repositories.com/f/graphics-multimedia/generative-camera-controls/prompt-based-camera-controls.md) — Enables cinematic camera control by parsing cinematography keywords in prompts to direct pans, tilts, and orbits. ### Part of an Awesome List - [Fluid Character Motion](https://awesome-repositories.com/f/awesome-lists/ai/motion-generation/fluid-character-motion.md) — Produces smooth, physically plausible movement for characters and objects without distortion in generated videos. ([source](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/assets/HunyuanVideo_1_5_Prompt_Handbook_EN.md)) ### User Interface & Experience - [Generative Video Styles](https://awesome-repositories.com/f/user-interface-experience/visual-styling-systems/visual-style-references/generative-video-styles.md) — Applies specified artistic or cinematic styles like photorealism or animation to generated videos. ([source](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/assets/HunyuanVideo_1_5_Prompt_Handbook_EN.md))