Introduction
Runway Gen-2 supports short-video generation conditioned on text and images. It is an important example of video generation becoming a product in 2023. Creative concerns expand from a single composition toward motion, camera behavior, temporal consistency and the demands of audiovisual production.
View full image ↗Poster frame for the iceberg example in Runway’s official Gen-2 demonstration, prompted as a top-down drone shot with muted colours. This is model-generated imagery.
Runway · Rights in the original image and document remain with their respective holders
Source · Gen-2 | Runway Research ↗RESEARCH ACCOUNT
Turning text, images and video into combinable shot inputs.
ANTI-AI ARCHIVE · Revised 2026-10-02
Multiple modes of generation
Runway’s Gen-2 research page distinguishes text-to-video, text-plus-image, image-to-video, stylisation, storyboarding, masking and rendering. These modes alter relationships between inputs and outputs; not every clip is generated from a sentence alone. Demonstrations and product claims should be distinguished from independently documented productions.
Section sources: Gen-2 multimodal video generation
The organisation of shot production
The system brings existing footage, composition and verbal intentions into a generative workflow. Documentation should identify what was filmed or designed by people, what the model supplied, and how editing connected the outputs. A model name cannot describe the production of an entire moving-image work.
Section sources: Gen-2 multimodal video generation
Sources for this account
Runway Gen-2 research page and descriptions of generation modes read.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning.
Compare the methods, forms of control or presentation contexts of this entry and Stable Video Diffusion.
Dates & version record
Date displayed for this node: 2023-06 · Historical date recorded for the source: 2023-06
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Gen-2 multimodal video generation
https://runwayml.com/research/gen-2
Current cited URL
Gen-2
https://runwayml.com/
URL cited in a research master or supplement; it may have moved or expired
Provenance, translation & verification
Timeline entry #198 · Historical node
Research materials & supplement references · 3
AI Art Genealogy Research Master · p. 31 · 107
Date as recorded: 2023-06
Gen-2 multimodal video generation ↗
Gen-2 multimodal video generation
GenAI Visual Release Chronology Research Master · p. 14 · R067
Date as recorded: 2023-06
Gen-2 multimodal video generation ↗
Gen-2
GenAI Visual Release Chronology Research Master · p. 14 · R069
Date as recorded: 2023-06
Gen-2 multimodal video generation ↗
Runway Gen-2
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Gen-2 multimodal video generation. Art-history node #198. https://salondesrefuses.cn/en/art-history/107
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.