# Sakuga-42M Dataset: Scaling Up Cartoon Research

arXiv: https://arxiv.org/abs/2405.07425 · HTML: https://mlsanity.com/paper/2405.07425/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 13 May 2024.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2403.06098/) (2024)
- [LDMVFI: Video Frame Interpolation with Latent Diffusion Models](https://mlsanity.com/paper/2303.09508/) (2023)
- [Learning Audio-Video Modalities from Image Captions](https://mlsanity.com/paper/2204.00679/) (2022)
- [Deep Animation Video Interpolation in the Wild](https://mlsanity.com/paper/2104.02495/) (2021)
- [Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties](https://mlsanity.com/paper/2311.17041/) (2023)
- [The Animation Transformer: Visual Correspondence via Segment Matching](https://mlsanity.com/paper/2109.02614/) (2021)
- [Automatic Temporally Coherent Video Colorization](https://mlsanity.com/paper/1904.09527/) (2019)
- [Learning Inclusion Matching for Animation Paint Bucket Colorization](https://mlsanity.com/paper/2403.18342/) (2024)
- [Deep Geometrized Cartoon Line Inbetweening](https://mlsanity.com/paper/2309.16643/) (2023)
- [Re:Draw -- Context Aware Translation as a Controllable Method for Artistic Production](https://mlsanity.com/paper/2401.03499/) (2024)

## Built on by (most cited first, 17 of 17)

- [PhysAnimator: Physics-Guided Generative Cartoon Animation](https://mlsanity.com/paper/2501.16550/) (2025)
- [AniDoc: Animation Creation Made Easier](https://mlsanity.com/paper/2412.14173/) (2024)
- [Generative AI for Cel-Animation: A Survey](https://mlsanity.com/paper/2501.06250/) (2025)
- [MangaNinja: Line Art Colorization with Precise Reference Following](https://mlsanity.com/paper/2501.08332/) (2025)
- [Follow-Your-Color: Multi-Instance Sketch Colorization](https://mlsanity.com/paper/2503.16948/) (2025)
- [AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era](https://mlsanity.com/paper/2412.10255/) (2024)
- [AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation](https://mlsanity.com/paper/2506.03126/) (2025)
- [AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction](https://mlsanity.com/paper/2504.01014/) (2025)
- [LongAnimation: Long Animation Generation with Dynamic Global-Local Memory](https://mlsanity.com/paper/2507.01945/) (2025)
- [OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer](https://mlsanity.com/paper/2604.24762/) (2026)
- [SketchColour: Channel Concat Guided DiT-based Sketch-to-Colour Pipeline for 2D Animation](https://mlsanity.com/paper/2507.01586/) (2025)
- [TimeColor: Flexible Reference Colorization via Temporal Concatenation](https://mlsanity.com/paper/2601.00296/) (2026)
- [InstanceAnimator: Multi-Instance Sketch Video Colorization](https://mlsanity.com/paper/2603.25357/) (2026)
- [MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation](https://mlsanity.com/paper/2507.20368/) (2025)
- [PTTA: A Pure Text-to-Animation Framework for High-Quality Creation](https://mlsanity.com/paper/2512.18614/) (2025)
- [SketchKeyAnime: Reference-anchored Sparse Key-Sketch Animation Synthesis](https://mlsanity.com/paper/2606.19958/) (2026)
- [PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos](https://mlsanity.com/paper/2608.00903/) (2026)

## Abstract (arXiv)

Hand-drawn cartoon animation employs sketches and flat-color segments to create the illusion of motion. While recent advancements like CLIP, SVD, and Sora show impressive results in understanding and generating natural video by scaling large models with extensive datasets, they are not as effective for cartoons. Through our empirical experiments, we argue that this ineffectiveness stems from a notable bias in hand-drawn cartoons that diverges from the distribution of natural videos. Can we harness the success of the scaling paradigm to benefit cartoon research? Unfortunately, until now, there has not been a sizable cartoon dataset available for exploration. In this research, we propose the Sakuga-42M Dataset, the first large-scale cartoon animation dataset. Sakuga-42M comprises 42 million keyframes covering various artistic styles, regions, and years, with comprehensive semantic annotations including video-text description pairs, anime tags, content taxonomies, etc. We pioneer the benefits of such a large-scale cartoon dataset on comprehension and generation tasks by finetuning contemporary foundation models like Video CLIP, Video Mamba, and SVD, achieving outstanding performance on cartoon-related tasks. Our motivation is to introduce large-scaling to cartoon research and foster generalization and robustness in future cartoon applications. Dataset, Code, and Pretrained Models will be publicly available.