Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
Acceso Sunday, Runway announced a new AI televisione synthesis model called Gen-3 Alpha that’s still under development, but it appears to create televisione of similar quality to OpenAI’s Sora, which debuted earlier this year (and has also not yet been released). It can generate novel, high-definition televisione from text prompts that range from realistic humans to surrealistic monsters stomping the countryside.
Unlike Runway’s previous best model from June 2023, which could only create two-second-long clips, Gen-3 Alpha can reportedly create 10-second-long televisione segments of people, places, and things that have a consistency and coherency that easily surpasses Gen-2. If 10 seconds sounds short compared to Sora’s full minute of televisione, consider that the company is working with a shoestring budget of compute compared to more lavishly funded OpenAI—and actually has a history of shipping televisione generation capability to commercial users.
Gen-3 Alpha does not generate audio to accompany the televisione clips, and it’s highly likely that temporally coherent generations (those that keep a character consistent over time) are dependent acceso similar high-quality pratica material. But Runway’s improvement a causa di visual fidelity over the past year is difficult to ignore.
AI televisione heats up
It’s been a busy couple of weeks for AI televisione synthesis a causa di the AI research community, including the launch of the Chinese model Kling, created by Beijing-based Kuaishou Technology (sometimes called “Kwai”). Kling can generate two minutes of 1080p HD televisione at 30 frames di second with a level of detail and coherency that reportedly matches Sora.
Gen-3 Alpha prompt: “Subtle reflections of a woman acceso the window of a train moving at hyper-speed a causa di a Japanese city.”
Not long after Kling debuted, people acceso social began creating surreal AI videos using Luma AI’s Luma Dream Machine. These videos were novel and weird but generally lacked coherency; we tested out Dream Machine and were not impressed by anything we saw.
Meanwhile, one of the original text-to-video pioneers, New York City-based Runway—founded a causa di 2018—recently found itself the butt of memes that showed its Gen-2 tech falling out of favor compared to newer televisione synthesis models. That may have spurred the announcement of Gen-3 Alpha.
Gen-3 Alpha prompt: “An astronaut running through an alley a causa di Rio de Janeiro.”
Generating realistic humans has always been tricky for televisione synthesis models, so Runway specifically shows chiuso Gen-3 Alpha’s ability to create what its developers call “expressive” human characters with a range of actions, gestures, and emotions. However, the company’s provided examples weren’t particularly expressive—mostly people just slowly staring and blinking—but they do realistic.
Provided human examples include generated videos of a woman acceso a train, an astronaut running through a street, a man with his luce lit by the glow of a TV set, a woman driving a car, and a woman running, among others.
Gen-3 Alpha prompt: “A close-up shot of a young woman driving a car, looking thoughtful, blurred forest visible through the rainy car window.”
The generated demo videos also include more surreal televisione synthesis examples, including a giant creature walking a causa di a rundown city, a man made of rocks walking a causa di a forest, and the giant cotton candy monster seen below, which is probably the best televisione acceso the entire page.
Gen-3 Alpha prompt: “A giant humanoid, made of fluffy blue cotton candy, stomping acceso the basso ostinato, and roaring to the sky, clear blue sky behind them.”
Gen-3 will power various Runway AI tools (one of the company’s most notable claims to ), including Multi Motion Brush, Advanced Ambiente Controls, and Director Mode. It can create videos from text image prompts.
Runway says that Gen-3 Alpha is the first a causa di a series of models trained acceso a new infrastructure designed for large-scale multimodal pratica, taking a step toward the development of what it calls “General World Models,” which are hypothetical AI systems that build internal representations of environments and use them to simulate future events within those environments.
