Recently, another innovative text-to-video AI generator named Hotshot has caught the eye, with the official videos showcasing truly impressive results!
You can experience the generated effects first-hand:
It is reported that this new Hotshot model can generate videos up to 10 seconds long and 720p resolution, and is very flexible in its creative styles, capable of showcasing different animation styles, such as comic book-like animations or rotoscope-style videos. Its highlights can be summarized as follows:
Text-to-Video Generation: Users can input text to generate 10-second 720p videos, supporting a fast and convenient creative process.
Watermark-Free Video Output: Videos generated by free users are watermark-free, providing more freedom for creators.
Diverse Video Styles: Hotshot can produce various styles of videos, including comic and dynamic image styles, meeting different creative needs.
High Adaptability and Scalability: The model has the potential to extend to longer video durations and higher resolutions, and may also support audio generation in the future.
Robust Technical Foundation: Hotshot is trained on 600 million video clips, utilizing a large number of GPUs, achieving efficient video generation.
This AI video generation model has now entered the public "early preview" phase, and users can experience this model for free on the Hotshot official website. However, it should be noted that the number of daily generations is limited to two videos, and the generated videos are watermark-free.
Hotshot's Backing Team Completed Model Training in Four Months
Hotshot's startup was founded in 2023 by Aakash Sastry, John Mullan, and Duncan Crawbuck.
Sastry stated on social media X: "For the first time in a decade, it's possible to build powerful and novel video applications for customers." This new Hotshot model is the foundation for achieving this goal, and they say it's just the beginning, with more surprises to come. Previously, Hotshot gained popularity as a free consumer AI photo creation and editing app, but now they have shifted their focus to this new text-to-video AI model.
According to Sastry, the Hotshot team completed the training of this model in just four months, which was no simple task! They used 600 million video clips and relied on thousands of GPUs for training, with technical challenges可想而知, and occasional machine failures causing headaches.
To ensure the smooth training of the model, their team members almost monitored the training process around the clock. Sastry also mentioned that they are exploring longer video durations and higher resolutions, and may even add audio elements in the future.
In his view, AI-generated content could become mainstream in digital media within the next 12 months, especially in YouTube video production, where creators will be able to fully control the generation process, from text to video, and even audio.
The AIbase team also tested Hotshot and found that the generated videos have potential, although the quality and details may not yet match some competitors. For example, by inputting the prompt "An ice sculptor carving an intricate design, chips flying as they work," the generated video effect is as follows:
The video movements are relatively smooth and realistic, but the clarity needs improvement. If you'd like to try it out, you can visit the following entry:
Product Entry:https://top.aibase.com/tool/hotshot
Key Points:
🌟 Hotshot's new text-to-video AI generator has entered the public "early preview" phase, allowing users to experience it for free.
🚀 The model was trained in just four months using 600 million video clips and thousands of GPUs, showing strong potential.
🎥 Founder Sastry predicts that within a year, AI-generated full YouTube videos will become common, giving creators more control.