From PC Mag: Adobe has cautiously dipped into generative AI with its Firefly technology, wary of low-quality results and treading on intellectual property rights. But at its Max conference this week, it unveiled a Firefly Video Model that supports text to video and image to video.
"Video generative AI is hard," Adobe’s VP of Generative AI, Alexandru Costin, said in a press briefing. The company is focused on features that creative professionals actually need, rather than buzzy tricks, but with the Firefly Video Model, it takes a few steps forward in offering generative AI for professionals.
The model will appear in the standalone Firefly web application. Text to video works by generating video content based on a text prompt, while image to video converts a still image into animated video content. Adobe trained the model on hundreds of millions of high-quality assets and applies Content Credentials to its creations to let the world know that they're AI-generated. The tool can generate both realistic and imaginary-looking scenes.
View: Full Article
