AI Paper Atlas

Research map / Video / Video generation

STIV: Scalable Text and Image Conditioned Video Generation

Zongyu Lin, Wei Liu, Chen Chen, Jiasen Lu, Wenze Hu, Tsu-Jui Fu, Jesse Allardice, Zhengfeng Lai, Liangchen Song, Bowen Zhang, Cha Chen, Yiran Fei and 4 more

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 17 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
add flow matching training objective (ablation)T2I-XL · T2I (GenEval)GenEval: 0.379 -> 0.457Improved
add CFG renormalization at inference (ablation)T2I-XL · COCOFID: 24.96 -> 21.16Improved
add internal bigG CLIP text encoder (ablation)T2I-XL · T2I (GenEval)GenEval: 0.492 -> 0.607Improved
add synthetic recaptions to original captions (ablation)T2I-XL · T2I (GenEval)GenEval: 0.607 -> 0.685Improved
add MaskDiT 50% spatial masking (ablation)T2I-XL · T2IFID and GenEval: FID 20.26 -> 23.85; GenEval 0.474 -> 0.499Mixed
use frame replacement instead of cross attention alone (ablation)STIV-XL · VBench-I2VAverage scores: 73.0 -> 77.3Improved
add large projection layer to FR + CA (ablation)STIV-XL · VBench-I2VDynamic Degree: 35.4 -> 22.4Hurt
add first frame loss to FR + CA + LP (ablation)STIV-XL · VBench-I2VAverage scores: 75.6 -> 75.3Hurt
add image condition dropout with JIT-CFG to a TI2V model (ablation)STIV-M-512 · VBench T2VTotal score: 66.1 -> 80.7Improved
add image condition dropout with JIT-CFG (ablation)STIV-M-512 · VBenchDynamic Degree: 10.2 -> 24.0Improved
add image condition dropout with JIT-CFG (ablation)STIV-M-512 · VBench-I2VTotal score: 90.1 -> 89.8Hurt
initialize TI2V from T2V instead of T2I (ablation)STIV-XL · VBench-I2VCam Mot: 29.8 -> 38.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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