Research map / Video / Video generation
From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition
Ling Lo, Kelvin C.K. Chan, Wen-Huang Cheng, Ming-Hsuan Yang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| apply transitional-direction guidance with neutral prompt anchoring on VideoCrafter2 | VideoCrafter2 · CAT-Bench | Wholistic Transition Score (overall): 0.0022 -> 0.1486 | Improved |
| add neutral prompt anchoring (anchor middle frame to a neutral prompt) (ablation) | transitional-direction guidance · qualitative example (car, sunny to rainy) | visual consistency | Improved |
| use full descriptive prompts instead of isolated attribute words for the transitional direction (ablation) | transitional-direction guidance · qualitative example (hat color) | transition precision | Improved |
| increase scale factor alpha from [0,1] to [0,2] (ablation) | transitional-direction guidance · qualitative example (sunny to rainy) | transition intensity | Improved |
| increase scale factor alpha to [0,5] (ablation) | transitional-direction guidance · qualitative example (sunny to rainy) | visual artifacts | Hurt |
| reduce sampling steps to 80% (ablation) | Ours · Inference time | seconds: 453.71 -> 349.23 | Improved |
| apply method to OpenSora backbone | OpenSora · CAT-Bench | Wholistic Transition Score: 0.0035 -> 0.1622 | Improved |
| apply method to OpenSora backbone | OpenSora · CAT-Bench | Background Consistency: 0.9701 -> 0.9602 | Hurt |
| apply method to VideoCrafter2 | VideoCrafter2 · CAT-Bench video quality | Dynamic Degree: 0.4750 -> 0.7083 | Improved |
| apply method to VideoCrafter2 | VideoCrafter2 · CAT-Bench video quality | Consistency: 0.9639 -> 0.9537 | No clear effect |
| use prompt interpolation (Gen-L, FreeNoise) for binary beard attribute | Gen-L / FreeNoise · CAT-Bench beard | Wholistic Transition Score: Gen-L 0.0015, FreeNoise 0.0003 vs Ours 0.0332 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- VideoCrafter2 — VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models (CVPR 2024) · better on 2 of 3 shared results
- FreeNoise — FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling (ICLR 2024) · better on 2 of 2 shared results
- Free-Bloom — Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator (NeurIPS 2023) · better on 2 of 2 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
- Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation (NeurIPS 2024 · similarity 0.88)
- Emergent Temporal Correspondences from Video Diffusion Transformers (NeurIPS 2025 · similarity 0.88)
- VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide (CVPR 2025 · similarity 0.88)
- TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models (CVPR 2024 · similarity 0.88)
- VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models (AAAI 2025 · similarity 0.87)
- VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models (NeurIPS 2024 · similarity 0.87)
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.
