diffusion models

Kuaishou Large Model

Jun 11, 2025 · Artificial Intelligence

12 Kuaishou Breakthrough Papers at CVPR 2025: Video Generation, Diffusion & Multimodal AI

CVPR 2025 in Nashville will feature 12 Kuaishou papers spanning large‑scale video datasets, quality assessment, 3D/4D reconstruction, controllable generation, diffusion scaling laws, multimodal simulation, and novel benchmarks, highlighting the company's cutting‑edge contributions to video AI research.

Computer Visiondiffusion modelslarge-scale datasets

0 likes · 21 min read

12 Kuaishou Breakthrough Papers at CVPR 2025: Video Generation, Diffusion & Multimodal AI

DataFunTalk

Jun 8, 2025 · Artificial Intelligence

Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches

The article examines the current dominance of diffusion models in commercial video generation, contrasts them with autoregressive methods, and details how the open‑source MAGI‑1 model combines both paradigms to achieve longer, more controllable video synthesis while addressing scalability and quality challenges.

AI researchMAGI-1autoregressive models

0 likes · 70 min read

Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches

Amap Tech

Jun 5, 2025 · Artificial Intelligence

How MVPainter Achieves Accurate, High‑Detail 3D Texture Generation with Multi‑View Diffusion

MVPainter introduces a fully open‑source pipeline that generates high‑quality, PBR‑compatible 3D textures from a single reference image and a white model by leveraging multi‑view diffusion, geometric control, and a human‑aligned evaluation framework, dramatically improving texture fidelity, alignment, and detail.

3D texture generationAIPBR

0 likes · 10 min read

How MVPainter Achieves Accurate, High‑Detail 3D Texture Generation with Multi‑View Diffusion

AntTech

Jun 4, 2025 · Artificial Intelligence

LLaDA and LLaDA‑V: Large Language Diffusion Models and Their Multimodal Extensions

This article presents the LLaDA series of diffusion‑based large language models, explains how their generative‑modeling principle yields language intelligence comparable to autoregressive models, and details the multimodal LLaDA‑V architecture, training methods, experimental results, and broader implications for AI research.

Large Language Modelsdiffusion modelsgenerative modeling

0 likes · 10 min read

LLaDA and LLaDA‑V: Large Language Diffusion Models and Their Multimodal Extensions

Alimama Tech

Apr 17, 2025 · Artificial Intelligence

PosterMaker: High-Quality Product Poster Generation with Accurate Text Rendering

PosterMaker leverages a ControlNet‑based TextRenderNet with character‑level visual features and a reward‑driven foreground‑extension detector to generate high‑quality product posters that accurately render Chinese text (over 90% sentence accuracy) while preserving product fidelity, and is already deployed in Alibaba’s AI creative tool.

E-commerce AIcharacter-level featuresdiffusion models

0 likes · 18 min read

PosterMaker: High-Quality Product Poster Generation with Accurate Text Rendering

DaTaobao Tech

Apr 7, 2025 · Artificial Intelligence

Flow Matching for Generative Modeling

Flow Matching reformulates generative modeling by learning a time‑dependent vector field that deterministically transports Gaussian noise to data, using a neural network trained with an analytically derived L2 loss, yielding simpler training, faster convergence, and deterministic sampling that matches or exceeds diffusion model quality.

AIcontinuous normalizing flowdiffusion models

0 likes · 13 min read

Tencent Cloud Developer

Mar 25, 2025 · Artificial Intelligence

Knowledge Distillation in Diffusion Models: Techniques and Applications

The article explains how knowledge distillation transfers capabilities from large to smaller diffusion models, covering hard and soft labels, temperature scaling, and contrasting it with data distillation, while detailing techniques such as consistency models, progressive distillation, adversarial distillation, and adversarial post‑training for model compression and step reduction.

adversarial post-trainingadversarial trainingconsistency models

0 likes · 19 min read

Knowledge Distillation in Diffusion Models: Techniques and Applications

Bilibili Tech

Dec 24, 2024 · Artificial Intelligence

AniSora: An Integrated System for Anime Video Generation with Data Flywheel, Controllable Diffusion Models, and Evaluation Benchmark

AniSora combines a 10‑million‑pair anime text‑video dataset, a controllable diffusion‑transformer with temporal‑mask conditioning for text‑to‑video, interpolation and region‑guided animation, and a 948‑video benchmark, delivering industry‑leading character and motion consistency and already powering low‑cost dynamic‑comic production for multiple IPs.

AI AnimationAnime Video GenerationDataset Benchmark

0 likes · 21 min read

AniSora: An Integrated System for Anime Video Generation with Data Flywheel, Controllable Diffusion Models, and Evaluation Benchmark

DaTaobao Tech

Dec 16, 2024 · Artificial Intelligence

Reference Image Generation for Subject‑Driven Diffusion

This work presents a subject‑driven diffusion pipeline that injects multi‑scale reference features (ReferenceNet‑style) into high‑fidelity backbones such as SD‑XL and Flux, enabling zero‑shot, fine‑grained product consistency across diverse scenes and outperforming current fine‑tuned and zero‑shot methods while noting limits in category coverage and human interactions.

AIDreamboothIP-Adapter

0 likes · 9 min read

Reference Image Generation for Subject‑Driven Diffusion

AntTech

Nov 27, 2024 · Artificial Intelligence

EchoMimicV2: An End-to-End Audio‑Driven Semi‑Body Human Animation Framework

EchoMimicV2, an open‑source project from Ant Group's Alipay AI team, introduces an end‑to‑end audio‑driven framework that generates high‑quality semi‑body portrait videos by jointly coordinating audio, pose, and image inputs, while addressing challenges of condition complexity, model stability, and computational cost.

AI researchDigital HumanMultimodal Generation

0 likes · 16 min read

EchoMimicV2: An End-to-End Audio‑Driven Semi‑Body Human Animation Framework

Alimama Tech

Nov 27, 2024 · Artificial Intelligence

FlowDCN: Efficient Arbitrary-Resolution Image Generation via Groupwise Multi‑Scale Deformable Convolution

FlowDCN introduces Groupwise‑MSDCN, a sparse deformable convolution that replaces attention, enabling efficient arbitrary‑resolution image generation with linear complexity, fewer parameters and FLOPs, and achieving state‑of‑the‑art FID scores on ImageNet while requiring far fewer training steps.

Image Generationarbitrary resolutiondeformable convolution

0 likes · 12 min read

FlowDCN: Efficient Arbitrary-Resolution Image Generation via Groupwise Multi‑Scale Deformable Convolution

JD Tech

Nov 15, 2024 · Artificial Intelligence

Reliable Feedback Network (RFNet) for Improving Usable Advertising Image Generation

The paper proposes a multimodal Reliable Feedback Network (RFNet) and a consistency‑regularized fine‑tuning method (RFFT) that dramatically increase the proportion of usable advertising images generated by diffusion models while preserving visual appeal, and introduces the large‑scale RF1M dataset for training and evaluation.

Image GenerationRFNetadvertising images

0 likes · 9 min read

Reliable Feedback Network (RFNet) for Improving Usable Advertising Image Generation

JD Retail Technology

Nov 14, 2024 · Artificial Intelligence

Improving Advertisement Image Generation with a Multimodal Reliable Feedback Network (ECCV 2024)

The paper introduces a Multimodal Reliable Feedback Network (RFNet) and a consistency‑condition regularization technique that together boost the usable rate of automatically generated advertisement images while preserving visual quality, supported by a new million‑image annotated dataset and extensive ECCV‑2024 experiments.

AIECCV2024advertisement generation

0 likes · 8 min read

Improving Advertisement Image Generation with a Multimodal Reliable Feedback Network (ECCV 2024)

Tencent Cloud Developer

Oct 30, 2024 · Artificial Intelligence

Comprehensive Survey of AIGC Research: Papers, Resources, and Technical Overview

This survey acts as a comprehensive portal that organizes AIGC research across seven domains—text, image, and audio generation, cross‑modal association, text‑guided image and audio synthesis, and supporting resources—detailing seminal models such as GPT, Diffusion, CLIP, DALL·E, Stable Diffusion, MusicLM, and key papers that shaped each field.

AIGCClipComputer Vision

0 likes · 19 min read

Comprehensive Survey of AIGC Research: Papers, Resources, and Technical Overview

Xiaohongshu Tech REDtech

Sep 19, 2024 · Artificial Intelligence

Target-Driven Distillation (TDD): A Multi‑Goal Distillation Method for Accelerating Diffusion Models

Target‑Driven Distillation (TDD) is a multi‑goal distillation method that flexibly selects short‑range target steps and decouples guidance during training, enabling 4‑to‑8‑step diffusion generation that preserves high‑resolution detail, works with LoRA, ControlNet, InstantID, and outperforms existing consistency distillation techniques in speed and quality.

AI accelerationImage Generationdiffusion models

0 likes · 9 min read

Target-Driven Distillation (TDD): A Multi‑Goal Distillation Method for Accelerating Diffusion Models

Alimama Tech

Aug 16, 2024 · Artificial Intelligence

SPLAM: Sub‑Path Linear Approximation for Accelerating Diffusion Model Sampling

SPLAM (Sub‑Path Linear Approximation Model) accelerates diffusion‑model image synthesis by linearly approximating short sub‑paths of the probability‑flow ODE, allowing high‑quality generation in as few as four steps, outperforming prior fast‑sampling methods on COCO benchmarks and being deployed in Alibaba Mama’s recommendation system.

AI image generationSPLAMdiffusion models

0 likes · 11 min read

SPLAM: Sub‑Path Linear Approximation for Accelerating Diffusion Model Sampling

Kuaishou Tech

Jul 31, 2024 · Artificial Intelligence

Kuaishou’s Kolors Text‑to‑Image Model: Architecture, Evaluation, and Real‑World Applications

The article presents a comprehensive overview of Kuaishou’s Kolors (formerly 可图) multimodal generative model, detailing its data collection strategy, diffusion‑based architecture, evaluation metrics, derived capabilities such as prompt refinement and interactive generation, and a range of practical applications from AI‑powered live‑stream gifts to virtual try‑on, while also offering strategic advice for the domestic visual‑generation community.

AI applicationsKolorsdiffusion models

0 likes · 27 min read

Kuaishou’s Kolors Text‑to‑Image Model: Architecture, Evaluation, and Real‑World Applications

Tencent Advertising Technology

Jul 31, 2024 · Artificial Intelligence

MimicMotion: A Controllable Video Generation Framework for High-Quality Human Motion Synthesis

MimicMotion is a controllable video generation framework that produces smooth, high-quality human motion videos by leveraging skeletal action guidance, addressing challenges in video generation such as limited length, weak controllability, and lack of dynamic detail.

AIAdvertising TechnologyMimicMotion

0 likes · 13 min read

MimicMotion: A Controllable Video Generation Framework for High-Quality Human Motion Synthesis

AntTech

Jul 24, 2024 · Artificial Intelligence

EchoMimic: An Open‑Source AIGC‑Driven Framework for 2D/3D Digital Human Generation

EchoMimic, an open‑source project from Ant Group, presents a flexible, audio‑ and pose‑driven digital human generation pipeline that combines 2D, 3D and AIGC techniques, reduces production costs, achieves real‑time inference, and includes a detailed architecture, related work analysis, and future research directions.

AIGCComputer VisionDigital Human

0 likes · 18 min read

EchoMimic: An Open‑Source AIGC‑Driven Framework for 2D/3D Digital Human Generation

Kuaishou Tech

Jul 11, 2024 · Artificial Intelligence

Kuaishou Open-Sources Kolors: A High-Performance Text-to-Image Model Rivaling Midjourney v6

Kuaishou has officially open-sourced Kolors, a state-of-the-art text-to-image diffusion model that leverages ChatGLM3 for advanced bilingual text understanding and employs a two-stage training strategy to achieve photographic image quality rivaling leading proprietary systems.

Computer VisionLarge Language ModelsText-to-Image Generation

0 likes · 8 min read

Kuaishou Open-Sources Kolors: A High-Performance Text-to-Image Model Rivaling Midjourney v6