Category: New Videos

Lemon Slice (formerly Infinity AI) makes it easy to create short, expressive videos starring digital characters that talk and emote. Whether you’re telling a story, making content for fun, or experimenting with video ideas, the platform offers a creative way to animate characters without needing advanced tools or editing skills. Some describe it as better than Heygen for less.

You can start with a character template and guide them through a scene with your script or audio. It’s designed for those who want to bring an idea to life visually—even if they’ve never made a video before. If you’re curious, you can check it out here: https://lemonslice.com/

Runway has introduced Gen-4, its latest update in AI video generation, and it’s catching attention for one very welcome reason—more consistency. If you’ve ever tried making AI-generated video, you know how tricky it is to keep the same characters looking the same across different scenes. Gen-4 aims to make that easier by helping maintain the same style, characters, and objects from one shot to the next.

This upgrade means users can now create smoother, more coherent videos without jarring shifts in appearance or tone. While it’s not perfect (what tool is?), it’s a big step toward making AI video creation more usable for those who want to tell stories that flow naturally. It’s still early days, but Gen-4 might just make experimenting with video a little more fun—and a lot less frustrating. Read more

Kuaishou’s latest release, Kling 2.0, offers users an enhanced experience in AI-driven video generation. This updated tool allows for the creation of videos up to two minutes long, featuring smoother motion and improved visual quality. The platform’s advancements in motion dynamics and visual aesthetics provide a more seamless and realistic output. You can use Kling 2.0 at https://app.klingai.com/

Google has introduced a new feature in its Gemini platform that allows users to generate short videos using simple text prompts. This tool, powered by Google’s Veo 2, enables the creation of 8-second, 720p videos. It’s designed to be accessible to a wide range of users, including students and content creators, by simplifying the video creation process. It emphasizes lifelike scenes and fluid character movements by understanding real-world physics and human motion, in order to deliver videos with cinematic quality. Additionally, Gemini offers a feature called Whisk Animate, which can transform static images into animated clips. These tools are available to Gemini Advanced users and Google One AI Premium subscribers. Learn more

ByteDance (TikToK) has introduced Seaweed, an AI video generation model that enables users to create short videos from text descriptions or images. Available through platforms like GoEnhance and Pollo AI, Seaweed offers tools for crafting brief, dynamic video clips.It can generate videos in real-time at resolutions up to 2K and 24 FPS (considerably higher than the competition).

Like with most other video generation tools, users can input a prompt or upload an image to generate a 5-second video, with options to adjust resolution and aspect ratio, but Seaweed can also generate videos from audio files and excels in creating videos with synchronized lip movements and speech rhythms. It also supports coherent single-shot and multi-shot long videos maintaining consistency in characters, style, and environment.

Pollo AI offers a user-friendly platform that brings together multiple AI models for video and image creation. Users can generate content by providing text prompts, images, or videos, and customize outputs with various styles and effects. The platform supports features like consistent character animation and video style transfers, allowing for a range of creative possibilities. What sets Pollo AI apart is its integration of diverse AI models, such as Kling AI, Runway, and Vidu AI, within a single interface. This consolidation simplifies the creative process by eliminating the need to navigate multiple platforms. Users can experiment with different models to achieve desired results, making it a practical choice for those looking to explore AI-generated content without extensive technical knowledge. For more information, visit Pollo AI.

OpenAI has expanded access to Sora, their text-to-video AI tool, giving Plus subscribers unlimited video generation capabilities while free users receive limited access. This update marks a significant shift from the previous waitlist system, democratizing access to this powerful creative tool that transforms simple text prompts into realistic videos up to 60 seconds long.

What makes this update special compared to similar offerings like Runway or Pika is the combination of Sora’s renowned quality with newfound accessibility. While competitors often maintain strict access controls or charge per generation, OpenAI has opted for a subscription model that allows unlimited creative experimentation for Plus members ($20/month). The free tier access, though limited, also opens the door for casual users to explore video generation without financial commitment—making advanced AI video creation accessible to everyday creators rather than just professionals or developers.

SandAI has introduced MAGI-1, an open-source tool designed to generate videos from text prompts. Unlike traditional methods that process entire videos at once, MAGI-1 creates videos in smaller segments, allowing for more manageable and efficient generation. This approach aims to provide users with a flexible way to produce videos that align with their creative vision. MAGI-1 supports various input types, including text descriptions, images, and existing videos, offering users multiple avenues to create or enhance video content. The tool is available on platforms like Hugging Face and GitHub, making it accessible for those interested in exploring its capabilities. For more information and to try out MAGI-1, you can visit their Hugging Face page or GitHub repository. Learn more.