A Human-Computer Collaborative Video Creation Paradigm Integrating Creative Intent Memory, Preference Feedback, and Editable Generation Control
Main Article Content
Abstract
This study proposes preference feedback learning and attribute decoupling control to solve the problems of continuous AIGC video production: fading the historical creative intent, inability to incorporate the user’s preference sustainably and content drift due to local edits. On top of multimodal conditional encoding, key-value memory retrieval and latent-space video diffusion generation, we develop a human-computer collaborative video generation system which combines creative intent memory, preference feedback and editable generation control. To model the interaction between different modalities —text, reference images, and historical information—cross-modal attention is used. It adopts short-term caching, long-term memory to maintain creation intention among rounds and adapts short-term caching and temporal constraints with spatial masking for attribute-level local editing and dynamically updates character, action, shot and style preferences from both explicit and implicit feedback. The results of 120 generation tasks indicate that the full model obtained a semantic consistency of 0.341, a 17.4 percentage point higher character retention of 91.8% and an average of 3.5 rounds of interaction compared to single-round prompts. The results show that this model improves cross-round semantic retention and personalized adaptation, and decreases repetitive interaction expenses in the continuous video creation, while maintaining local editing stability.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Bervar M, Bertoncel T, Bach P M, “Generative Artificial Intelligence and the Creative Industries: A Bibliometric Review and Research Agenda[J],” Systems, vol. 14, no. 2, pp. 138–138, 2026.
Rakesh K V, Mazumdar S, Maity P R, et al., “Advancements in talking head generation: a comprehensive review of techniques, metrics, and challenges[J],” The Visual Computer, vol. 42, no. 1, pp. 9–9, 2025.
Oskooei R A, Caglar E, ¸Sahin I, et al., “Generative AI for Video Translation: A Scalable Architecture for Multilingual Video Conferencing[J],” Applied Sciences, vol. 15, no. 23, pp. 12691–12691, 2025.
Naser A Y, Sharma S, Niure K, et al., “Geographic prompting and content fidelity in generative Artificial Intelligence: A multi-model study of de-mographics and imaging equipment in AI-generated videos and images of Canadian medical radiation technologists.[J],” Journal of medical imaging and radiation sciences, vol. 56, no. 6, p. 102122, 2025.
Oppenlaender J, Linder R, Silvennoinen J, “Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering[J],” International Journal of Human–Computer Interaction, vol. 41, no. 16, pp. 10207– 10229, 2025.
Kranzle T, Sharratt K, “Evaluating Creative Output With Generative Artificial Intelligence: Comparing GPT Models and Human Experts in Idea Evaluation[J],” Creativity and Innovation Management, vol. 34, no. 4, pp. 991–1012, 2025.
Chompunuch S, Lubart T, “AI as a Helper: Leveraging Generative AI Tools Across Common Parts of the Creative Process[J],” Journal of Intelligence, vol. 13, no. 5, pp. 57–57, 2025.
Avlonitou C, Papadaki E, “AI: An Active and Innovative Tool for Artistic Creation[J],” Arts, vol. 14, no. 3, pp. 52–52, 2025.
Son M, Lee S, “Advancing Multimodal Large Language Models: Optimizing Prompt Engineering Strategies for Enhanced Performance[J],” Applied Sciences, vol. 15, no. 7, pp. 3992–3992, 2025.
Mzwri K, Szabo T M, “The Impact of Prompt Engineering and a Generative AI-Driven Tool on Autonomous Learning: A Case Study[J],” Education Sciences, vol. 15, no. 2, pp. 199–199, 2025.
Vinchon F, Gironnay V, Lubart T, “GenAI Creativity in Narrative Tasks: Exploring New Forms of Creativity[J],” Journal of Intelligence, vol. 12, no. 12, pp. 125–125, 2024.
Yan L, Greiff S, Teuber Z, et al., “Promises and challenges of generative artificial intelligence for human learning.[J],” Nature human behaviour, vol. 8, no. 10, pp. 1839–1850, 2024.
Luther T, Kimmerle J, Cress U, “Teaming Up with an AI: Exploring Human–AI Collaboration in a Writing Scenario with ChatGPT[J],” AI, vol. 5, no. 3, pp. 1357–1376, 2024.
Doshi R A, Hauser P O, “Generative AI enhances individual creativity but reduces the collective diversity of novel content.[J],” Science advances, vol. 10, no. 28, p. eadn5290, 2024.
Pitrez C J, “Generative Artificial Intelligence Image Tools among Future Designers: A Usability, User Experience, and Emotional Analysis[J],” Digital, vol. 4, no. 2, pp. 316–., 2024.
O’Toole K, Horvát Á E, “Extending human creativity with AI[J],” Journal of Creativity, vol. 34, no. 2, pp. 100080–., 2024.
Alfaleh M, “Human–AI Co-Agency for Competency-Based Talent Development: A Framework Integrating Creativity, Cognitive Skills, and Ethical Collaboration[J],” Journal of Intelligence, vol. 14, no. 7, p. 144, 2026.
Hikmet ¸S, Ozay N, “Human–AI collaboration in architectural design education: towards a conceptual framework[J],” Buildings, vol. 16, no. 6, p. 1097, 2026.
Dai C P, Yang M, Lee S, “Designing Human–AI Collaboration for Hybrid Intelligence in Immersive Learning Environments: A Conceptual Framework[J],” Systems, vol. 14, no. 6, p. 639, 2026.
McGuire J, De Cremer D, Van de Cruys T, “Establishing the importance of co-creation and self-efficacy in creative collaboration with artificial intelligence[J],” Scientific Reports, vol. 14, no. 1, p. 18525, 2024