Introducing SkyReels V3
A multi-modal video generation and editing model, featuring video extension, artistic stylization, in-video editing, and multi-person lip-sync.
More Consistency,
More Condition,
More Control
With multimodal input, the new SkyReels V3 model has more context to ensure the consistency of the final result. We support extending a video to generate a new shot, or adding, removing, and modifying the elements in it. You can also directly transform a video into a completely new style. The powerful audio-driven feature enables more refined multi-person dialogues, making the video no longer monotonous.
Video extension with new shots
Transform your video by generating shots from multiple viewpoints, bringing more diversity to every scene
Modify your video with multi-modal references
With SkyReels V3, you can combine text instructions, reference images, and masks for precise edits, while preserving most of the original video's motion. You can add, replace or just remove subjects from the video.
High-fidelity style transfer
SkyReels V3's video style transfer is more than just a superficial color transfer. It achieves a deep, semantic understanding of style characteristics to maintain exceptional consistency. Even with significant motion, it robustly preserves the coherence of the style, subjects, and environment.
Lip-sync for multi-person dialogues
SkyReels V3 is the world’s first AI model to enable multi-person dialogues, delivering lifelike, context-aware interactions. AI Avatars adapt seamlessly to any narrative, adding cinematic depth and unmatched realism to your stories.
Create without boundaries.
SkyReels API makes it possible.
Discover SkyReels’ latest and most advanced AI models to unlock new creative possibilities. Contact us at service@skyreels.ai to learn more.
Research that Inspires Progress
Explore research that turns imagination into reality. From smarter perception to dynamic world simulation, our work is shaping tomorrow’s intelligent experiences.
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers
The generation and editing of audio-conditioned talking portraits guided by multimodal inputs, including text, images, and videos, remains under explored. In this paper, we present SkyReels-Audio, a unified framework for synthesizing high-fidelity and temporally coherent talking portrait videos. Built upon pretrained video diffusion transformers, our framework supports infinite-length generation and editing, while enabling diverse and controllable conditioning through multimodal inputs. We employ a hybrid curriculum learning strategy to progressively align audio with facial motion, enabling fine-grained multimodal control over long video sequences. To enhance local facial coherence, we introduce a facial mask loss and an audio-guided classifier-free guidance mechanism. A sliding-window denoising approach further fuses latent representations across temporal segments, ensuring visual fidelity and temporal consistency across extended durations and diverse identities. More importantly, we construct a dedicated data pipeline for curating high-quality triplets consisting of synchronized audio, video, and textual descriptions. Comprehensive benchmark evaluations show that SkyReels-Audio achieves superior performance in lip-sync accuracy, identity consistency, and realistic facial dynamics, particularly under complex and challenging conditions.
SkyReels-A2: Compose Anything in Video Diffusion Transformers
This paper presents SkyReels-A2, a controllable video generation framework capable of assembling arbitrary visual elements (e.g., characters, objects, backgrounds) into synthesized videos based on textual prompts while maintaining strict consistency with reference images for each element. We term this task elements-to-video (E2V), whose primary challenges lie in preserving the fidelity of each reference element, ensuring coherent composition of the scene, and achieving natural outputs. To address these, we first design a comprehensive data pipeline to construct prompt-reference-video triplets for model training. Next, we propose a novel image-text joint embedding model to inject multi-element representations into the generative process, balancing element-specific consistency with global coherence and text alignment. We also optimize the inference pipeline for both speed and output stability. Moreover, we introduce a carefully curated benchmark for systematic evaluation, i.e, A2 Bench. Experiments demonstrate that our framework can generate diverse, high-quality videos with precise element control. SkyReels-A2 is the first open-source commercial grade model for the generation of E2V, performing favorably against advanced closed-source commercial models. We anticipate SkyReels-A2 will advance creative applications such as drama and virtual e-commerce, pushing the boundaries of controllable video generation.
SkyReels-V2: Infinite-length Film Generative Model
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity.
SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers
We present SkyReels-A1, a simple yet effective framework built upon video diffusion Transformer to facilitate portrait image animation. Existing methodologies still encounter issues, including identity distortion, background instability, and unrealistic facial dynamics, particularly in head-only animation scenarios. Besides, extending to accommodate diverse body proportions usually leads to visual inconsistencies or unnatural articulations. To address these challenges, SkyReels-A1 capitalizes on the strong generative capabilities of video DiT, enhancing facial motion transfer precision, identity retention, and temporal coherence. The system incorporates an expression-aware conditioning module that enables seamless video synthesis driven by expression-guided landmark inputs. Integrating the facial image-text alignment module strengthens the fusion of facial attributes with motion trajectories, reinforcing identity preservation. Additionally, SkyReels-A1 incorporates a multi-stage training paradigm to incrementally refine the correlation between expressions and motion while ensuring stable identity reproduction. Extensive empirical evaluations highlight the model's ability to produce visually coherent and compositionally diverse results, making it highly applicable to domains such as virtual avatars, remote communication, and digital media generation.
SkyReels V1: Human-Centric Video Foundation Model
SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips, SkyReels V1 offers three key advantages: Open-Source Leadership - Our Text-to-Video model achieves state-of-the-art (SOTA) performance among open-source models, comparable to proprietary models like Kling and Hailuo; Advanced Facial Animation - Captures 33 distinct facial expressions with over 400 natural movement combinations, accurately reflecting human emotions; Cinematic Lighting and Aesthetics - Trained on high-quality Hollywood-level film and television data, each generated frame exhibits cinematic quality in composition, actor positioning, and camera angles.