arXiv subjects

Zhengcong Fei

Publications and source records attributed to Zhengcong Fei.

At least 19 recordsLinked to original sources

arXiv2026

SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model

SkyReels V4 is a unified multi modal video foundation model for joint video audio generation, inpainting, and editing. The model adopts a dual stream Multimodal Diffusion Transformer (MMDiT) architecture, where one branch synthesizes video and the other generates temporally aligned audio, while sharing a powerful text encoder based on the Multimodal Large Language Models (MLLM). SkyReels V4 accepts rich multi modal instructions, including text, images, video clips, masks, and audio references. By combining the MLLMs multi modal instruction following capability with in context learning in the video branch MMDiT, the model can inject fine grained visual guidance under complex conditioning, while the audio branch MMDiT simultaneously leverages audio references to guide sound generation. On the video side, we adopt a channel concatenation formulation that unifies a wide range of inpainting style tasks, such as image to video, video extension, and video editing under a single interface, and naturally extends to vision referenced inpainting and editing via multi modal prompts. SkyReels V4 supports up to 1080p resolution, 32 FPS, and 15 second duration, enabling high fidelity, multi shot, cinema level video generation with synchronized audio. To make such high resolution, long-duration generation computationally feasible, we introduce an efficiency strategy: Joint generation of low resolution full sequences and high-resolution keyframes, followed by dedicated super-resolution and frame interpolation models. To our knowledge, SkyReels V4 is the first video foundation model that simultaneously supports multi-modal input, joint video audio generation, and a unified treatment of generation, inpainting, and editing, while maintaining strong efficiency and quality at cinematic resolutions and durations.

cs.CV↗

arXiv2026

SkyReels-V3 Technique Report

Video generation serves as a cornerstone for building world models, where multimodal contextual inference stands as the defining test of capability. In this end, we present SkyReels-V3, a conditional video generation model, built upon a unified multimodal in-context learning framework with diffusion Transformers. SkyReels-V3 model supports three core generative paradigms within a single architecture: reference images-to-video synthesis, video-to-video extension and audio-guided video generation. (i) reference images-to-video model is designed to produce high-fidelity videos with strong subject identity preservation, temporal coherence, and narrative consistency. To enhance reference adherence and compositional stability, we design a comprehensive data processing pipeline that leverages cross frame pairing, image editing, and semantic rewriting, effectively mitigating copy paste artifacts. During training, an image video hybrid strategy combined with multi-resolution joint optimization is employed to improve generalization and robustness across diverse scenarios. (ii) video extension model integrates spatio-temporal consistency modeling with large-scale video understanding, enabling both seamless single-shot continuation and intelligent multi-shot switching with professional cinematographic patterns. (iii) Talking avatar model supports minute-level audio-conditioned video generation by training first-and-last frame insertion patterns and reconstructing key-frame inference paradigms. On the basis of ensuring visual quality, synchronization of audio and videos has been optimized. Extensive evaluations demonstrate that SkyReels-V3 achieves state-of-the-art or near state-of-the-art performance on key metrics including visual quality, instruction following, and specific aspect metrics, approaching leading closed-source systems. Github: https://github.com/SkyworkAI/SkyReels-V3.

cs.CV↗

arXiv2025

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.

cs.CV↗

arXiv2025

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. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.

cs.CV↗

arXiv2025

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.

cs.CV↗

arXiv2025

Video Diffusion Transformers are In-Context Learners

This paper investigates a solution for enabling in-context capabilities of video diffusion transformers, with minimal tuning required for activation. Specifically, we propose a simple pipeline to leverage in-context generation: ($\textbf{i}$) concatenate videos along spacial or time dimension, ($\textbf{ii}$) jointly caption multi-scene video clips from one source, and ($\textbf{iii}$) apply task-specific fine-tuning using carefully curated small datasets. Through a series of diverse controllable tasks, we demonstrate qualitatively that existing advanced text-to-video models can effectively perform in-context generation. Notably, it allows for the creation of consistent multi-scene videos exceeding 30 seconds in duration, without additional computational overhead. Importantly, this method requires no modifications to the original models, results in high-fidelity video outputs that better align with prompt specifications and maintain role consistency. Our framework presents a valuable tool for the research community and offers critical insights for advancing product-level controllable video generation systems. The data, code, and model weights are publicly available at: https://github.com/feizc/Video-In-Context.

cs.CV↗

arXiv2025

Ingredients: Blending Custom Photos with Video Diffusion Transformers

This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as Ingredients. Generally, our method consists of three primary modules: (i) a facial extractor that captures versatile and precise facial features for each human ID from both global and local perspectives; (ii) a multi-scale projector that maps face embeddings into the contextual space of image query in video diffusion transformers; (iii) an ID router that dynamically combines and allocates multiple ID embedding to the corresponding space-time regions. Leveraging a meticulously curated text-video dataset and a multi-stage training protocol, Ingredients demonstrates superior performance in turning custom photos into dynamic and personalized video content. Qualitative evaluations highlight the advantages of proposed method, positioning it as a significant advancement toward more effective generative video control tools in Transformer-based architecture, compared to existing methods. The data, code, and model weights are publicly available at: https://github.com/feizc/Ingredients.

cs.CV↗

arXiv2025

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.

cs.CV↗

arXiv2024

FLUX that Plays Music

This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Flux\footnote{https://github.com/black-forest-labs/flux} model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. In between, coarse textual information, in conjunction with time step embeddings, is utilized in a modulation mechanism, while fine-grained textual details are concatenated with the music patch sequence as inputs. Through an in-depth study, we demonstrate that rectified flow training with an optimized architecture significantly outperforms established diffusion methods for the text-to-music task, as evidenced by various automatic metrics and human preference evaluations. Our experimental data, code, and model weights are made publicly available at: \url{https://github.com/feizc/FluxMusic}.

cs.SD↗

arXiv2024

Scaling Diffusion Transformers to 16 Billion Parameters

In this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert routing and expert-level balance loss, thereby capturing common knowledge and reducing redundancy among the different routed experts. When applied to conditional image generation, a deep analysis of experts specialization gains some interesting observations: (i) Expert selection shows preference with spatial position and denoising time step, while insensitive with different class-conditional information; (ii) As the MoE layers go deeper, the selection of experts gradually shifts from specific spacial position to dispersion and balance. (iii) Expert specialization tends to be more concentrated at the early time step and then gradually uniform after half. We attribute it to the diffusion process that first models the low-frequency spatial information and then high-frequency complex information. Based on the above guidance, a series of DiT-MoE experimentally achieves performance on par with dense networks yet requires much less computational load during inference. More encouragingly, we demonstrate the potential of DiT-MoE with synthesized image data, scaling diffusion model at a 16.5B parameter that attains a new SoTA FID-50K score of 1.80 in 512$\times$512 resolution settings. The project page: https://github.com/feizc/DiT-MoE.

cs.CV↗

arXiv2024

Dimba: Transformer-Mamba Diffusion Models

This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and Mamba layers, and integrate conditional information through the cross-attention layer, thus capitalizing on the advantages of both architectural paradigms. We investigate several optimization strategies, including quality tuning, resolution adaption, and identify critical configurations necessary for large-scale image generation. The model's flexible design supports scenarios that cater to specific resource constraints and objectives. When scaled appropriately, Dimba offers substantial throughput and a reduced memory footprint relative to conventional pure Transformers-based benchmarks. Extensive experiments indicate that Dimba achieves comparable performance compared with benchmarks in terms of image quality, artistic rendering, and semantic control. We also report several intriguing properties of architecture discovered during evaluation and release checkpoints in experiments. Our findings emphasize the promise of large-scale hybrid Transformer-Mamba architectures in the foundational stage of diffusion models, suggesting a bright future for text-to-image generation.

cs.CV↗

arXiv2024

Music Consistency Models

Consistency models have exhibited remarkable capabilities in facilitating efficient image/video generation, enabling synthesis with minimal sampling steps. It has proven to be advantageous in mitigating the computational burdens associated with diffusion models. Nevertheless, the application of consistency models in music generation remains largely unexplored. To address this gap, we present Music Consistency Models (\texttt{MusicCM}), which leverages the concept of consistency models to efficiently synthesize mel-spectrogram for music clips, maintaining high quality while minimizing the number of sampling steps. Building upon existing text-to-music diffusion models, the \texttt{MusicCM} model incorporates consistency distillation and adversarial discriminator training. Moreover, we find it beneficial to generate extended coherent music by incorporating multiple diffusion processes with shared constraints. Experimental results reveal the effectiveness of our model in terms of computational efficiency, fidelity, and naturalness. Notable, \texttt{MusicCM} achieves seamless music synthesis with a mere four sampling steps, e.g., only one second per minute of the music clip, showcasing the potential for real-time application.

cs.SD↗

arXiv2024

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models

Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with extra conditions, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage manifests in its reduced spatial aggregation complexity, rendering it exceptionally adept at processing high-resolution images, thereby eliminating the necessity for windowing or group cached operations. Experimental results on both condition and unconditional image generation tasks demonstrate that Diffison-RWKV achieves performance on par with or surpasses existing CNN or Transformer-based diffusion models in FID and IS metrics while significantly reducing total computation FLOP usage.

cs.CV↗

arXiv2024

Scalable Diffusion Models with State Space Backbone

This paper presents a new exploration into a category of diffusion models built upon state space architecture. We endeavor to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space backbone, functioning on raw patches or latent space. Given its notable efficacy in accommodating long-range dependencies, Diffusion State Space Models (DiS) are distinguished by treating all inputs including time, condition, and noisy image patches as tokens. Our assessment of DiS encompasses both unconditional and class-conditional image generation scenarios, revealing that DiS exhibits comparable, if not superior, performance to CNN-based or Transformer-based U-Net architectures of commensurate size. Furthermore, we analyze the scalability of DiS, gauged by the forward pass complexity quantified in Gflops. DiS models with higher Gflops, achieved through augmentation of depth/width or augmentation of input tokens, consistently demonstrate lower FID. In addition to demonstrating commendable scalability characteristics, DiS-H/2 models in latent space achieve performance levels akin to prior diffusion models on class-conditional ImageNet benchmarks at the resolution of 256$\times$256 and 512$\times$512, while significantly reducing the computational burden. The code and models are available at: https://github.com/feizc/DiS.

cs.CV↗

arXiv2024

A-JEPA: Joint-Embedding Predictive Architecture Can Listen

This paper presents that the masked-modeling principle driving the success of large foundational vision models can be effectively applied to audio by making predictions in a latent space. We introduce Audio-based Joint-Embedding Predictive Architecture (A-JEPA), a simple extension method for self-supervised learning from the audio spectrum. Following the design of I-JEPA, our A-JEPA encodes visible audio spectrogram patches with a curriculum masking strategy via context encoder, and predicts the representations of regions sampled at well-designed locations. The target representations of those regions are extracted by the exponential moving average of context encoder, \emph{i.e.}, target encoder, on the whole spectrogram. We find it beneficial to transfer random block masking into time-frequency aware masking in a curriculum manner, considering the complexity of highly correlated in local time and frequency in audio spectrograms. To enhance contextual semantic understanding and robustness, we fine-tune the encoder with a regularized masking on target datasets, instead of input dropping or zero. Empirically, when built with Vision Transformers structure, we find A-JEPA to be highly scalable and sets new state-of-the-art performance on multiple audio and speech classification tasks, outperforming other recent models that use externally supervised pre-training.

cs.SD↗

arXiv2023

Tuning-Free Inversion-Enhanced Control for Consistent Image Editing

Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e.g., changing postures) to the main objects in the input image without changing their identity or attributes. To guarantee consistent attributes, some existing methods fine-tune the entire model or the textual embedding for structural consistency, but they are time-consuming and fail to perform non-rigid edits. Other works are tuning-free, but their performances are weakened by the quality of Denoising Diffusion Implicit Model (DDIM) reconstruction, which often fails in real-world scenarios. In this paper, we present a novel approach called Tuning-free Inversion-enhanced Control (TIC), which directly correlates features from the inversion process with those from the sampling process to mitigate the inconsistency in DDIM reconstruction. Specifically, our method effectively obtains inversion features from the key and value features in the self-attention layers, and enhances the sampling process by these inversion features, thus achieving accurate reconstruction and content-consistent editing. To extend the applicability of our method to general editing scenarios, we also propose a mask-guided attention concatenation strategy that combines contents from both the inversion and the naive DDIM editing processes. Experiments show that the proposed method outperforms previous works in reconstruction and consistent editing, and produces impressive results in various settings.

cs.CV↗

arXiv2023

Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning

While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In this work, we propose a lightweight image captioning network in combination with continuous diffusion, called Prefix-diffusion. To achieve diversity, we design an efficient method that injects prefix image embeddings into the denoising process of the diffusion model. In order to reduce trainable parameters, we employ a pre-trained model to extract image features and further design an extra mapping network. Prefix-diffusion is able to generate diverse captions with relatively less parameters, while maintaining the fluency and relevance of the captions benefiting from the generative capabilities of the diffusion model. Our work paves the way for scaling up diffusion models for image captioning, and achieves promising performance compared with recent approaches.

cs.CV↗

arXiv2023

Progressive Text-to-Image Generation

Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space. Although the simple generative process surprisingly works well, is this the best way to generate the image? For instance, human creation is more inclined to the outline-to-fine of an image, while VQ-AR models themselves do not consider any relative importance of image patches. In this paper, we present a progressive model for high-fidelity text-to-image generation. The proposed method takes effect by creating new image tokens from coarse to fine based on the existing context in a parallel manner, and this procedure is recursively applied with the proposed error revision mechanism until an image sequence is completed. The resulting coarse-to-fine hierarchy makes the image generation process intuitive and interpretable. Extensive experiments in MS COCO benchmark demonstrate that the progressive model produces significantly better results compared with the previous VQ-AR method in FID score across a wide variety of categories and aspects. Moreover, the design of parallel generation in each step allows more than $\times 13$ inference acceleration with slight performance loss.

cs.CV↗