At its annual I/O event, Google introduced a new AI-based application called Flow, positioned as a creative toolkit for video makers. This new platform, an evolution of the earlier experimental VideoFX project, merges Google’s recent progress in image, video, and language generation. The goal: make it easier for storytellers to conceptualize, draft, and refine video sequences using AI.
Flow acts as a hybrid tool that builds on Veo for generating video, Imagen for producing images, and Gemini for orchestrating the process through natural language. Together, these tools enable users to sketch out scenes, animate sequences, and adjust visuals with text prompts. Rather than generating videos in chunks, creators now gain a system that manages assets and prompts in one place, making the production pipeline more cohesive.
Veo 2, the improved video model underneath Flow, adds motion and realism in a way meant to mimic physics. Whether or not it convinces experts on visual accuracy, the model marks a step forward in dynamic content creation. With Imagen, users can create visual assets from scratch and bring them into their Flow projects. Then, Gemini helps fine-tune output, adjusting timing, mood, or even narrative arcs through conversational inputs.
One major appeal lies in Flow’s handling of visual consistency. Scenes blend into one another with more continuity than earlier AI systems typically allow. Filmmakers can not only edit transitions but also set camera positions, plan pans, and tweak angles — previously rigid aspects of AI video now made adjustable. There’s also manual control over extending shots, allowing more creative flexibility across each segment.
For creators frustrated by scattered generations and unstructured assets, Flow introduces a management system that organizes files, clips, and even the text used to create them. That brings it closer to a proper editing environment, though it’s still grounded in AI-generation rather than traditional footage.
To add credibility, Google worked with professional directors and visual artists during Flow’s development phase. Their feedback helped refine interface and control features, shaping what eventually launched today.
Currently, Flow is accessible to users in the U.S. subscribed to either the AI Pro or AI Ultra tiers. The Pro plan includes 100 video generations per month, while Ultra subscribers receive unlimited generations and earlier access to Veo 3, which will support built-in audio.
As AI-generated content inches closer to cinematic quality, Flow looks like a calculated step to move these tools from lab demos into practical workflows. For now, it remains to be seen how professionals and indie creators alike adopt it — and whether AI can finally match the fluidity of human storytelling.
Read next: Google Just Launched a Tool That Tells You If Something Was Made by Its AI
Flow acts as a hybrid tool that builds on Veo for generating video, Imagen for producing images, and Gemini for orchestrating the process through natural language. Together, these tools enable users to sketch out scenes, animate sequences, and adjust visuals with text prompts. Rather than generating videos in chunks, creators now gain a system that manages assets and prompts in one place, making the production pipeline more cohesive.
Veo 2, the improved video model underneath Flow, adds motion and realism in a way meant to mimic physics. Whether or not it convinces experts on visual accuracy, the model marks a step forward in dynamic content creation. With Imagen, users can create visual assets from scratch and bring them into their Flow projects. Then, Gemini helps fine-tune output, adjusting timing, mood, or even narrative arcs through conversational inputs.
One major appeal lies in Flow’s handling of visual consistency. Scenes blend into one another with more continuity than earlier AI systems typically allow. Filmmakers can not only edit transitions but also set camera positions, plan pans, and tweak angles — previously rigid aspects of AI video now made adjustable. There’s also manual control over extending shots, allowing more creative flexibility across each segment.
For creators frustrated by scattered generations and unstructured assets, Flow introduces a management system that organizes files, clips, and even the text used to create them. That brings it closer to a proper editing environment, though it’s still grounded in AI-generation rather than traditional footage.
To add credibility, Google worked with professional directors and visual artists during Flow’s development phase. Their feedback helped refine interface and control features, shaping what eventually launched today.
Currently, Flow is accessible to users in the U.S. subscribed to either the AI Pro or AI Ultra tiers. The Pro plan includes 100 video generations per month, while Ultra subscribers receive unlimited generations and earlier access to Veo 3, which will support built-in audio.
As AI-generated content inches closer to cinematic quality, Flow looks like a calculated step to move these tools from lab demos into practical workflows. For now, it remains to be seen how professionals and indie creators alike adopt it — and whether AI can finally match the fluidity of human storytelling.
Read next: Google Just Launched a Tool That Tells You If Something Was Made by Its AI
