Edited Endpoints as Partial Goals for Image-to-Video Generation

Sihyun Kim; Sanghyun Jo; Kyungsu Kim

cs.CVOct 29, 2026

Edited Endpoints as Partial Goals for Image-to-Video Generation

Authors: Sihyun Kim, Sanghyun Jo, Kyungsu Kim

Organizations: Seoul National University · OGQ

Abstract

Edited endpoint images make the target of an image-to-video transition explicit and can improve transition completion, but also preserve context in the source image's layout. Full-frame endpoint conditioning turns this preserved context into requirements on the video's final state, potentially inducing temporal artifacts. We measure discontinuity with Hard-Cut (HC), late background reversal with Background Motion Reversal (BMR), and motion suppression with Dynamic Degree (DD). These artifacts appear across five video models spanning training-free and learned endpoint conditioning, in model-specific forms. We study Partial, a selective conditioning scheme that constrains only an edit-relevant region estimated from image-editor attention and leaves the remaining terminal content to the video model. Across three backbones on TC-Bench-I2V, Partial reduces temporal artifacts relative to full-frame conditioning, with no significant difference in Transition Completion Ratio (TCR); on Wan2.2-Turbo, uniformly weakening conditioning does not reproduce these reductions. A donor-context intervention keeps full-frame conditioning and replaces only the context outside the edit-relevant region with the final frame of a Partial video. It lowers HC and BMR on HunyuanVideo-1.5 and lowers BMR while restoring DD on Wan2.2-Turbo, with no significant difference in TCR, so constraint extent alone does not account for these artifacts. Together, these findings suggest that edited endpoints should serve as partial future goals, although edit relevance does not guarantee future validity. Code and data will be released at https://github.com/wannagetacat/Edited-Endpoints-I2V.

Figures & tables

Figure 1: Edited endpoints preserve context that need not specify the video’s future. Full-frame endpoint conditioning constrains both requested appearance and preserved context. Partial constrains only estimated edit-relevant support $M_{0}$ from image-editor attention (blue outline); washed-out positions retain the video prediction. Source frame: DAVIS bus [ 32 ] , via FiVE-Bench [ 20 ] .

Figure 2: Partial reduces temporal artifacts relative to Full. Paired differences with 95% CIs over 103 prompts and five seeds; open markers are not significant. Tables 1 and C1 give levels and intervals.

Figure 3: Terminal content, not only constraint extent, affects temporal artifacts. (a) The donor-context endpoint keeps the edited endpoint inside $M_{0}$ (blue outline) and uses the final frame of a paired Partial rollout outside it (orange tint). Original and Donor-context Full share the Full projection and the recipient seed; a cross-seed donor comes from another seed of the same prompt. (b) Donor-context minus Original Full with paired 95% CIs over 103 prompts and five seeds; open markers are not significant; gray ticks mark Partial minus Original Full. (c) HunyuanVideo-1.5, prompt 28, seed 22004: native frames and consecutive-frame CLIP similarity; the Original Full discontinuity between frames 114 and 117 is absent under Donor-context Full.

Figure 4: Estimated edit-relevant support does not guarantee a future-valid terminal constraint. Wan2.2-Turbo, purple-bus example of Fig. 1 (case 90001, outside TC-Bench), seed 22001. (a) Saved $M_{0}$ outline (blue) and token-pooled weights (tint). (b) Partial: the boxed sign is absent at native frames 108 and 112, then reappears at 114. Identical regions are enlarged below.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Figure A1: Estimated edit-relevant support. Source images, edited endpoints, and GMM–Ising masks for TC-Bench prompts 0, 5, and 82. Blue marks support; percentages give constrained area before token pooling.

Figure A2: Endpoints from three editors. Source images and edited endpoints for TC-Bench prompts 0, 103, and 105. FLUX.2 and Qwen-Image-Edit use the final-frame prompt in Appendix A ; ChronoEdit uses the original transition prompt to match its formulation of editing as video generation.

Analysis	Population and reference
Main backbone comparisons	103 prompts $\times$ 5 seeds per condition; Table 1 .
Wan2.2-Turbo spatial controls	103 prompts $\times$ 5 seeds per support, paired with the main Wan2.2-Turbo Partial (TCR 42.91%).
HunyuanVideo-1.5 donor-context intervention	Original Full reuses the main cohort. Donor P regenerates main Partial with identical settings; TCR 44.66% versus 44.47% reflects run-to-run variation.
HunyuanVideo-1.5 cross-seed donors	O, same-seed D, and P are reused; 515 new $D_{\rm cross}$ videos use a donor-seed assignment fixed before generation.
Wan2.2-Turbo donor-context intervention	O, D, N, and P are new 515-video runs sharing one noise stream per prompt–seed. P reproduces main Partial’s HC, DD, and BMR exactly; TCR 42.72% versus 42.91% reflects re-judging variation. O regenerates Full with this noise stream and stays within sampling variation of main Full on all four metrics (TCR 43.30% versus 41.94%, HC 6.49 versus 6.47, DD 65.44% versus 66.80%, BMR 0.600 versus 0.599; no paired difference is significant).
HC model-judge agreement	90 prompts $\times$ 2 samples $\times$ 9 conditions; 1,619 evaluable videos. HunyuanVideo-1.5 is excluded.

Appendix

Table B1: Appendix populations and references. Counts refer to paired prompt–seed positions unless stated otherwise.

Figure C1: Completion requires covering the edit-relevant support. Wan2.2-Turbo, paired

\Delta

TCR relative to Partial with 95% CIs over 103 prompts and five seeds; open markers are not significant. (a) Supports with exactly

|M_{0}|

cells covering 0–75% of

M_{0}

, the rest placed outside it; 100% is Partial. (b) Supports placed without reference to

M_{0}

, which cover 8–10% of it by chance. The dashed line marks Endpoint-free.

Condition	Inside $M_{0}$	Outside $M_{0}$	Support
O: Original Full	Original latent	Original latent	Full
D: Donor-context Full	Original latent	Re-encoded donor final RGB	Full
$D_{\rm cross}$ : Cross-seed donor	Original latent	Re-encoded final RGB of another seed’s donor	Full
N: Native-latent Full	Original latent	Native donor tail latent	Full
P: Partial donor	Original latent	Video prediction retained	$M_{0}$

Appendix

Table D1: Donor-context construction. O/D/

D_{\rm cross}

/N all retain Full support. Content inside

M_{0}

always comes from the original edited endpoint.

Figure F1: A residual failure of fixed support. (a) The edited endpoint preserves an occluding bus-stop sign; blue shows $M_{0}$ , and the red box defines the crop. (b) Identical image-coordinate crops at all eight original frame indices. Red borders mark the sign’s reappearance in Partial and random release; attention-ranked and adaptive release avoid it in this example. The release variants are exploratory. All rows use Wan2.2-Turbo, purple-bus case 90001 and seed 22001, as in Fig. 4 ; frame intervals are unequal.

Image-to-Video Generation

Image-to-video generation creates coherent moving clips from still images, guided by learned models and controls such as motion, camera, or text.

See all 96 papers

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
Oct 27, 2026Yijing Lin, Zhendong Mao, Mengqi Huang +2Conditional Image Generation Subject-Driven Image Generation
University of Science and Technology of China
VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
Oct 8, 2026Leigang Qu, Feng Cheng, Ziyan Yang +7Video Editing Instruction-Based Video Editing
National University of Singapore · ByteDance Seed · University of Science and Technology of China
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
Mar 16, 2026Ruonan Yu, Zhenxiong Tan, Zigeng Chen +2Diffusion-Based Video Editing Video Editing
National University of Singapore · Shanghai Jiao Tong University

Oct 27, 2026J/K move · Enter open · S save

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

Yijing Lin, Zhendong Mao, Mengqi Huang, Yuxin Wang+1

University of Science and Technology of China

Conditional Image Generation Subject-Driven Image Generation Image Editing

Open paper AskPDF arXiv

Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance. Pretrained video models provide a promising foundation by encoding visual transformations across time, yet existing approaches typically assign the condition and target to fixed temporal positions. We observe that condition-target relationships vary substantially across generation tasks, while video models naturally encode visual transformations at different temporal scales. This motivates us to model conditional generation through input-adaptive virtual temporal relations. We propose FrameForge, which captures two complementary aspects of such relations. Mixture of Temporal Experts (MoTE) models how far the target lies from the condition by dynamically selecting temporal RoPE experts with different virtual intervals. Chain of Temporal Reasoning (CoTR) models how the condition is transformed into the target through a latent intermediate state, with a reasoning-bottleneck attention mask encouraging information propagation through this pathway. Experiments on DreamBench, COCO2017, and GEdit-Bench show that FrameForge achieves superior performance in subject-driven generation, canny-to-image generation, and image editing among the compared methods.

Abstract

Image-to-Video Generation

Explore similar work

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer