# BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations

arXiv: https://arxiv.org/abs/2501.07647 · HTML: https://mlsanity.com/paper/2501.07647/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 42)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models](https://mlsanity.com/paper/2309.15103/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)

## Built on by (most cited first, 15 of 15)

- [InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions](https://mlsanity.com/paper/2506.09984/) (2025)
- [OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation](https://mlsanity.com/paper/2603.30045/) (2026)
- [Chain of Event-Centric Causal Thought for Physically Plausible Video Generation](https://mlsanity.com/paper/2603.09094/) (2026)
- [On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise](https://mlsanity.com/paper/2504.09789/) (2025)
- [TempoControl: Temporal Attention Guidance for Text-to-Video Models](https://mlsanity.com/paper/2510.02226/) (2025)
- [TTOM: Test-Time Optimization and Memorization for Compositional Video Generation](https://mlsanity.com/paper/2510.07940/) (2025)
- [SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation](https://mlsanity.com/paper/2604.05489/) (2026)
- [BlobCtrl: Taming Controllable Blob for Element-level Image Editing](https://mlsanity.com/paper/2503.13434/) (2025)
- [LatentMove: Towards Complex Human Movement Video Generation](https://mlsanity.com/paper/2505.22046/) (2025)
- [CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models](https://mlsanity.com/paper/2509.08015/) (2025)
- [Comp-Attn: Present-and-Align Attention for Compositional Video Generation](https://mlsanity.com/paper/2503.14428/) (2025)
- [Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models](https://mlsanity.com/paper/2511.20587/) (2025)
- [Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization](https://mlsanity.com/paper/2608.13037/) (2026)
- [Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning](https://mlsanity.com/paper/2609.00656/) (2026)
- [LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation](https://mlsanity.com/paper/2609.38146/) (2026)

## Abstract (arXiv)

Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual primitives - blob video representation, a general representation for controllable video generation. Based on blob conditions, we develop a blob-grounded video diffusion model named BlobGEN-Vid that allows users to control object motions and fine-grained object appearance. In particular, we introduce a masked 3D attention module that effectively improves regional consistency across frames. In addition, we introduce a learnable module to interpolate text embeddings so that users can control semantics in specific frames and obtain smooth object transitions. We show that our framework is model-agnostic and build BlobGEN-Vid based on both U-Net and DiT-based video diffusion models. Extensive experimental results show that BlobGEN-Vid achieves superior zero-shot video generation ability and state-of-the-art layout controllability on multiple benchmarks. When combined with an LLM for layout planning, our framework even outperforms proprietary text-to-video generators in terms of compositional accuracy.