Introduction
Facial performance transfer turns a driving performance into generated character animation, expanding control over acting.
View full image ↗Frame at 2 seconds from Runway’s official Act-One demonstration, illustrating character performance generation. The image shows the demo’s animated character.
Runway · Rights in the original image and document remain with their respective holders
Source · Runway Research | Introducing Act-One ↗RESEARCH ACCOUNT
Using an actor’s performance to drive character animation.
ANTI-AI ARCHIVE · Revised 2026-10-02
Release and use
Runway introduced Act-One on 22 October 2024 as a way to drive character expression and movement from performance video and audio within Gen-3 Alpha. Its demonstrations emphasised ordinary camera recordings rather than a full facial motion-capture setup, including reference characters with proportions different from the performer’s. The resulting performance therefore has a filmed human input: it is not simply acting invented from a written prompt.
Section sources: Introducing Act-One
Change in creative practice
This workflow makes it important to distinguish the performer, character designer and generative system. A changed appearance does not erase the source of timing, expressive choices or gestures. Historically, the significant question is how performance travels between a body and a synthetic figure, rather than whether the performer has disappeared from production.
Section sources: Introducing Act-One
Sources for this account
Official release scope and demonstration descriptions read; vendor performance claims are not treated as independent test results.
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 Movie Gen.
Compare the methods, forms of control or presentation contexts of this entry and Aleph video editing.
Dates & version record
Date displayed for this node: 2024-10-22 · Historical date recorded for the source: 2024-10
Date corrected from the cited official release announcement; the master date is retained for comparison.
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.
Act-One
https://runwayml.com/
URL cited in a research master or supplement; it may have moved or expired
This is the archive’s bilingual research abstract. The external link is an original source, not a claim that the publisher offers full text in both languages.
Provenance, translation & verification
Timeline entry #260 · Product / model
Research materials & supplement references · 1
GenAI Visual Release Chronology Research Master · p. 25 · R132
Date as recorded: 2024-10
Act-One ↗
Act-One
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. Act-One. Art-history node #260. https://salondesrefuses.cn/en/art-history/187
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.