The Verge: Hollywood’s AI Future Is Bespoke Workflows, Not Vanilla Prompts
The Verge AI17 hours agoCommentaryThe article reviews AI-assisted films shown at the 2026 Tribeca Film Festival and finds a clear divide between rough prompt-driven work and more carefully directed workflows. Google DeepMind’s Dear Upstairs Neighbors is presented as the strongest case, using custom Veo and Imagen models trained on human-made concept art. The Verge concludes that Hollywood’s likely AI future is bespoke studio tooling guided by artists, not commercially viable films generated from generic prompts.
Douyin Recruits AI Video Talent as Creators Eye AI Upside
量子位 QbitAI3 days agoBusinessBased only on the title, the article reports that Douyin is seeking “AI video talent,” likely targeting creators skilled in AI-assisted video production. The framing suggests QbitAI sees this as more than a routine creator campaign, presenting it as a possible way for creators to capture value from AI tools. No specific program details, eligibility rules, compensation, models, or product features are provided in the available source text.
AI Short-Drama Tools Sector Lands Its Largest Single Funding Round of the Year
量子位 QbitAI3 days agoBusinessThe AI short-drama tools market has recorded its biggest single financing event of the year, signaling strong investor conviction in AI-assisted video storytelling. Short-drama — episodic vertical-video content — has become one of the fastest-growing entertainment formats in China and beyond. The milestone round underscores how purpose-built AI production tools are attracting serious capital as the format scales globally.
ByteDance Open-Sources Bernini, a Unified Framework for AI Video Editing★ 74
量子位 QbitAI5 days agoReleaseByteDance’s commercial technology team has open-sourced Bernini, a unified framework for AI video generation and editing. Its design separates semantic planning from visual rendering: an MLLM-based planner understands text, source videos, images, and video references, then a DiT-based renderer produces the final video. The released Bernini-R includes inference code and weights, while the full planner-enabled version is still being prepared.
JoyAI-Echo open-source framework targets stable 5-minute AI long videos★ 72
量子位 QbitAI6 days agoNew ToolQbitAI reports that JD’s team has open-sourced JoyAI-Echo, a long audio-video generation framework for multi-minute AI videos. It targets character drift, unstable voice, slow inference, and blurry output through cross-modal memory, memory-driven post-training, and lightweight real-time super-resolution. The system also includes a Director Agent for script planning, shot-level generation, localized edits, and iterative video production.
Introducing ElevenLabs Image & Video
ElevenLabs Blog6 days agoNew ToolElevenLabs Image & Video Beta brings image, video, voice, music, and sound effects into a single platform. It integrates models such as Veo, Sora, Kling, Wan, Seedance, GPT Image, Flux Kontext, Seedream, and Nanobanana. The product targets creators, marketers, educators, freelancers, and content teams making social content, product videos, and educational materials.
如何使用 Seedance 2.0 製作出色的 AI 影片★ 70
Replicate Blog60 days agoTutorial### A New Era of AI Video Generation: Why Now Is the Best Time With the rapid evolution of generative AI technology, video generation has transformed from an…
如何使用圖片引導 Veo 3 進行影片生成：Replicate 最新指南★ 75
Replicate Blog317 days agoTutorialThis article from Replicate explains how to use images to prompt Veo 3, the latest AI video generation model. As AI video technology advances rapidly, using…