The evolution of Text-to-Video is moving fast. I’ve been testing some of the latest models, combining image input with text-driven generation to see how they perform. The result? A short action sequence starring… me. (Check out the video!)
For this, I experimented with Kling 1.6 and S2V-01 from MiniMax, looking at how they handle motion coherence, character consistency, and scene composition. The improvements in AI-generated video are noticeable, and it’s interesting to see how different models approach the challenge.
At this rate, we might not be too far from being able to generate entire movies with just text prompts. Curious to see where this will go in the next few years.
The evolution of Text-to-Video is moving fast. I’ve been testing some of the latest models, combining image input with text-driven generation to see how they perform. The result? A short action sequence starring… me. (Check out the video!)
For this, I experimented with Kling 1.6 and S2V-01 from MiniMax, looking at how they handle motion coherence, character consistency, and scene composition. The improvements in AI-generated video are noticeable, and it’s interesting to see how different models approach the challenge.
At this rate, we might not be too far from being able to generate entire movies with just text prompts. Curious to see where this will go in the next few years.