Etiquetas: text-to-video

OpenAI is reportedly preparing to bring its AI video generator, Sora, into the ChatGPT interface. The move would let users create short video clips from simple text prompts without leaving the chat. Sora, first launched as a standalone app, would remain functional while gaining broader accessibility through ChatGPT. Although no official announcement has been made, insiders say the integration is slated for the near future, positioning OpenAI to compete more aggressively in the text‑to‑video market. Leer más

Runway announced its new Gen-4.5 text-to-video AI model, claiming it delivers unprecedented physical accuracy and visual precision. The model reportedly handles complex prompts better, rendering realistic object motion, fluid dynamics, and a range of visual styles without sacrificing video quality. While rolling out gradually to all users, Runway acknowledges limitations in object permanence and causal reasoning. The release coincides with OpenAI’s own advances, including its Sora 2 model, which also emphasizes realistic physics. Both companies aim to make AI‑generated video increasingly lifelike and difficult to distinguish from real footage. Leer más

OpenAI has released its text‑to‑video generative AI app, Sora, on the Google Play Store for Android users, while the iOS version remains limited to select markets and invitation‑only access. The Android launch quickly attracted a large user base, reportedly surpassing one million downloads within a few days. At the same time, the app has faced criticism for allowing disrespectful depictions of historic figures such as Martin Luther King Jr., prompting censure from the Japanese government over anime‑style copies. OpenAI also contends with a copyright lawsuit from Cameo and has introduced a new “cameo” feature that integrates existing personalities into AI‑generated videos. Leer más

The generative‑AI market is expanding into video, with major tech firms releasing text‑to‑video models such as OpenAI's Sora and Google's Veo 3. These tools create short clips from prompts or images, often lasting only a few seconds, and some include synchronized audio. Other companies—including Adobe, Midjourney, Runway, Luma, Pika, and Ideogram—offer comparable services, typically on a paid basis. While the technology promises new creative possibilities, it also brings challenges like hallucinations and unresolved legal and ethical questions. The ecosystem remains fast‑moving, with many products still evolving. Leer más

Google announced Veo 3.1, the latest upgrade to its AI video model, promising stronger prompt adherence, higher realism, and improved audio. The new version expands format support to include both landscape and portrait 16:9 video, addressing the surge in vertical content on platforms like YouTube Shorts and TikTok. A "Fast" variant aims to reduce compute costs, and the model will be integrated across Google’s ecosystem, including the Flow filmmaking tool. While the upgrade raises concerns about distinguishing real from synthetic media, it positions Google more competitively against rivals such as OpenAI's Sora. Leer más