AI Paper Atlas

Research map / Video / Video generation

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

Hanzhuo Huang, Yufan Feng, Cheng Shi, Lan Xu, Jingyi Yu, Sibei Yang

NeurIPS 2023 · Video › Video generation · approach: Compositional text-to-video diffusion · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace joint noise initialization with independent noise (ablation)Free-Bloom · qualitative frame consistencycontent consistencyImproved
add step-aware self-attention shift to contextual frames (ablation)Free-Bloom · qualitative identical/temporal coherencecoherenceImproved
add attention to the current frame itself (vs TAV spatio-temporal attention only) (ablation)Free-Bloom · qualitative semantic alignmentsemantic coherenceImproved
shift attention across denoising steps rather than concatenating current and contextual attention without shifting (ablation)Free-Bloom · qualitative semanticssemantic coherenceImproved
use sin/cos weighted noise mixing instead of linear (1-lambda, lambda) weighting (ablation)Free-Bloom joint noise · qualitative image qualityframe validityImproved
add serial LLM prompts to Text2Video-Zero (ablation)Text2Video-Zero · qualitativesemantic progressionNo clear effect
balance dual-path interpolation coefficient m(t) (vs mostly contextual path or mostly denoising path) (ablation)Free-Bloom interpolation · qualitative interpolationframe qualityImproved
compare Free-Bloom to trained VideoFusion on temporal coherenceFree-Bloom · User studyTemporal coherence (1-5): 3.267 vs 3.889Hurt
compare Free-Bloom to T2V-Zero on fidelityFree-Bloom · User studyFidelity (1-5): 3.486 -> 4.133Improved
score CLIP against serial LLM prompts instead of input promptFree-Bloom · CLIP metricsCLIP score: 0.477 -> 0.482Improved

Later papers that compared with this method

1 later accepted paper reports Free-Bloom as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy