A new, uncensored AI video model may spark a new AI hobbyist movement

December 19, 2024:


“A muscular barbarian breaking a CRT television set with a weapon, cinematic, 8K, studio lighting”


“A scared woman in a Victorian outfit running through a forest, dolly shot”


“Low angle static shot: A teddy bear sitting on a picnic blanket in a park, eating a slice of pizza. The teddy bear is brown and fluffy, with a red bowtie, and the pizza slice is gooey with cheese and pepperoni. The sun is setting, casting a golden glow over the scene”


“Aerial shot of a small American town getting deluged with liquid cheese after a massive cheese rainstorm where liquid cheese rained down and dripped all over the buildings”


Also, we added a new one: “A young woman doing a complex floor gymnastics routine at the Olympics, featuring running and flips.”


Weighing the results

Overall, the results shown above seem fairly comparable to Gen-3 Alpha and Minimax video-01, and that’s notable because HunyuanVideo can be downloaded for free, fine-tuned, and run locally in an uncensored way (given the appropriate hardware).

There are some flaws, of course. The vaudeville robots are not animals, the cat is drinking from a weird transparent beer can, and the man eating spaghetti is obviously not Will Smith. There appears to be some celebrity censorship in the metadata/labeling of the training data, which differs from Kling and Minimax’s AI video offerings. And yes, the gymnast has some anatomical issues.

Source link