Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/

Evaluating Text-to-Image Synthesis with a Conditional Fréchet Distance

Evaluating text-to-image synthesis is challenging due to misalignment between established metrics and human preferences. We propose cFreD, a metric based on the notion of Conditional Fr\'echet Distance that explicitly accounts for both visual fidelity and text-prompt alignment. Existing metrics such as Inception Score (IS), Fr\'echet Inception Distance (FID) and CLIPScore assess either image quality or image-text alignment but not both which limits their correlation with human preferences. Scoring models explicitly trained to replicate human preferences require constant updates and may not generalize to novel generation techniques or out-of-domain inputs. Through extensive experiments across multiple recently proposed text-to-image models and diverse prompt datasets, we demonstrate that cFreD exhibits a higher correlation with human judgments compared to statistical metrics, including metrics trained with human preferences. Our findings validate cFreD as a robust, future-proof metric for the systematic evaluation of text-to-image models, standardizing benchmarking in this rapidly evolving field. We release our evaluation toolkit and benchmark in the appendix.

Synthetic Video Enhances Physical Fidelity in Video Synthesis

We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respect real-world physics, such as maintaining 3D consistency, and serve as a valuable resource that can potentially improve video generation models. To harness this potential, we propose a solution that curates and integrates synthetic data while introducing a method to transfer its physical realism to the model, significantly reducing unwanted artifacts. Through experiments on three representative tasks emphasizing physical consistency, we demonstrate its efficacy in enhancing physical fidelity. While our model still lacks a deep understanding of physics, our work offers one of the first empirical demonstrations that synthetic video enhances physical fidelity in video synthesis. Website: https://kevinz8866.github.io/simulation/

Long Context Tuning for Video Generation

Recent advances in video generation can produce realistic, minute-long single-shot videos with scalable diffusion transformers. However, real-world narrative videos require multi-shot scenes with visual and dynamic consistency across shots. In this work, we introduce Long Context Tuning (LCT), a training paradigm that expands the context window of pre-trained single-shot video diffusion models to learn scene-level consistency directly from data. Our method expands full attention mechanisms from individual shots to encompass all shots within a scene, incorporating interleaved 3D position embedding and an asynchronous noise strategy, enabling both joint and auto-regressive shot generation without additional parameters. Models with bidirectional attention after LCT can further be fine-tuned with context-causal attention, facilitating auto-regressive generation with efficient KV-cache. Experiments demonstrate single-shot models after LCT can produce coherent multi-shot scenes and exhibit emerging capabilities, including compositional generation and interactive shot extension, paving the way for more practical visual content creation. See https://guoyww.github.io/projects/long-context-video/ for more details.

Is Your Text-to-Image Model Robust to Caption Noise?

In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates from the visual reality, the ramifications of such caption hallucinations on T2I generation performance remain under-explored. Through our empirical investigation, we first establish a comprehensive dataset comprising VLM-generated captions, and then systematically analyze how caption hallucination influences generation outcomes. Our findings reveal that (1) the disparities in caption quality persistently impact model outputs during fine-tuning. (2) VLMs confidence scores serve as reliable indicators for detecting and characterizing noise-related patterns in the data distribution. (3) even subtle variations in caption fidelity have significant effects on the quality of learned representations. These findings collectively emphasize the profound impact of caption quality on model performance and highlight the need for more sophisticated robust training algorithm in T2I. In response to these observations, we propose a approach leveraging VLM confidence score to mitigate caption noise, thereby enhancing the robustness of T2I models against hallucination in caption.

PropTest: Automatic Property Testing for Improved Visual Programming

Visual Programming has emerged as an alternative to end-to-end black-box visual reasoning models. This type of methods leverage Large Language Models (LLMs) to decompose a problem and generate the source code for an executable computer program. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code that tests for visual properties in an initial round of proposed solutions. Particularly, our method tests for data-type consistency, as well as syntactic and semantic properties in the generated solutions. Our proposed solution outperforms baselines and achieves comparable results to state-of-the-art methods while using smaller and publicly available LLMs (CodeLlama-7B and WizardCoder-15B). This is demonstrated across different benchmarks on visual question answering and referring expression comprehension, showing the efficacy of our approach in enhancing the performance and generalization of visual reasoning tasks. Specifically, PropTest improves ViperGPT by obtaining 48.66% accuracy (+8.3%) on the A-OKVQA benchmark and 52.8% (+3.3%) on the RefCOCO+ benchmark using CodeLlama-7B.

Learning from Models and Data for Visual Grounding

We introduce SynGround, a novel framework that combines data-driven learning and knowledge transfer from various large-scale pretrained models to enhance the visual grounding capabilities of a pretrained vision-and-language model. The knowledge transfer from the models initiates the generation of image descriptions through an image description generator. These descriptions serve dual purposes: they act as prompts for synthesizing images through a text-to-image generator, and as queries for synthesizing text, from which phrases are extracted using a large language model. Finally, we leverage an open-vocabulary object detector to generate synthetic bounding boxes for the synthetic images and texts. We finetune a pretrained vision-and-language model on this dataset by optimizing a mask-attention consistency objective that aligns region annotations with gradient-based model explanations. The resulting model improves the grounding capabilities of an off-the-shelf vision-and-language model. Particularly, SynGround improves the pointing game accuracy of ALBEF on the Flickr30k dataset from 79.38% to 87.26%, and on RefCOCO+ Test A from 69.35% to 79.06% and on RefCOCO+ Test B from 53.77% to 63.67%.

Improved Visual Grounding through Self-Consistent Explanations

Vision-and-language models trained to match images with text can be combined with visual explanation methods to point to the locations of specific objects in an image. Our work shows that the localization --"grounding"-- abilities of these models can be further improved by finetuning for self-consistent visual explanations. We propose a strategy for augmenting existing text-image datasets with paraphrases using a large language model, and SelfEQ, a weakly-supervised strategy on visual explanation maps for paraphrases that encourages self-consistency. Specifically, for an input textual phrase, we attempt to generate a paraphrase and finetune the model so that the phrase and paraphrase map to the same region in the image. We posit that this both expands the vocabulary that the model is able to handle, and improves the quality of the object locations highlighted by gradient-based visual explanation methods (e.g. GradCAM). We demonstrate that SelfEQ improves performance on Flickr30k, ReferIt, and RefCOCO+ over a strong baseline method and several prior works. Particularly, comparing to other methods that do not use any type of box annotations, we obtain 84.07% on Flickr30k (an absolute improvement of 4.69%), 67.40% on ReferIt (an absolute improvement of 7.68%), and 75.10%, 55.49% on RefCOCO+ test sets A and B respectively (an absolute improvement of 3.74% on average).

SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data

We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of $\langle$subject, relation, object$\rangle$ triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for $\langle$subject, relation, object$\rangle$ triplets for which no object locations are available during training, we are able to obtain a recall@3 of 42.59% for relation-object pairs and 32.27% for their box locations.

Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations

We propose a margin-based loss for vision-language model pretraining that encourages gradient-based explanations that are consistent with region-level annotations. We refer to this objective as Attention Mask Consistency (AMC) and demonstrate that it produces superior visual grounding performance compared to models that rely instead on region-level annotations for explicitly training an object detector such as Faster R-CNN. AMC works by encouraging gradient-based explanation masks that focus their attention scores mostly within annotated regions of interest for images that contain such annotations. Particularly, a model trained with AMC on top of standard vision-language modeling objectives obtains a state-of-the-art accuracy of 86.59% in the Flickr30k visual grounding benchmark, an absolute improvement of 5.48% when compared to the best previous model. Our approach also performs exceedingly well on established benchmarks for referring expression comprehension and offers the added benefit by design of gradient-based explanations that better align with human annotations.