|
Powered by LightX2V inference framework to enable low‑cost, high-throughput video generation
HONG KONG, Dec. 22, 2025 /PRNewswire/ -- SenseTime launched its Seko 2.0, a multi-episode drama generation agent tailored for short drama and motion comic creators. Supporting production up to 100-episode series, Seko 2.0 ensures consistency in characters, scenes, and props across episodes. It significantly boosts production efficiency, reducing comic drama production time by 80% to 90% compared to traditional methods.
Seko 2.0 is powered by SenseTime's open‑source LightX2V framework, the industry's first inference framework capable of real‑time video generation. This innovative framework allows for cost-effective and high-throughput video production.
Supporting 100-episode series generation
First launched in July 2025, Seko attracted over 100,000 creators within two months and its user base surpassed 200,000 in less than half a year, 30% of which were short drama creators and 20% comic drama creators.
The new Seko 2.0 further lowers the creative threshold and enables more efficient video production. Its key upgraded features include:
- A revamped User Interface (UI) with optimized visual presentation, delivering an immersive creative experience.
- Multi-episode generation capability with long-context management, supporting the creation up to 100 episodes.
- Intelligent Agent scheduling, enabling flexible association of characters, scenes, and props across episodes, with character makeup and styling adaptable to different scenarios.
Xu Li, Chairman of the Board and CEO of SenseTime, stated: "Seko will open a door for people, who have creative imagination, but lack of professional production capabilities, so they can truly enter the creative ecosystem and unleash their imagination." He added that, as AI capabilities continue to evolve, the quality of generated episodes will gradually move up, generating both refined "high-brow" works and popular "low-brow" content that can coexist harmoniously.
AI comic and short dramas have experienced an explosive growth in China. Data shows that the supply of comic dramas in mainland China surged at compound annual growth rate (CAGR) of 83% in the first half of this year. Meanwhile, more than 3,000 works were produced with total revenues jumping by 12 times. Many individual creators and small teams have joined this creative trend, some even taking it as their second career.
Enabling multi-person lip-sync & audio-visual synchronization
Most existing AI video generation products on the market only support single-episode short films or clip production. To meet creators' urgent demand for high-quality, large-scale multi-episode production, Seko 2.0 achieves two core technology breakthroughs:
1) SekoIDX: Achieving character consistency across multi-episode and cross-shot scenarios
Maintaining character consistency across episodes and shots has long been an industry challenge. Traditional generation methods often result in characters appearing as "copied and pasted" (lacking vividness) or "unrecognizable" when responding to new motion or expression promots. By introducing "negative reference images" in the high-noise phase of diffusion models, SekoIDX ensures character consistency across multi-episode and cross-shot content while avoiding excessive similarity to reference images. It also maintains high stability when responding to commands for different expressions, poses, and scenes.
2) SekoTalk: Realizing multi-person lip-sync and natural audio-visual synchronization
Traditional digital human technology often suffers from inaccurate lip-sync in complex scenarios involving multi-language and multi-person interactions. As the industry's first solution supporting lip-sync for more than two people, SekoTalk achieves highly precise audio-visual synchronization from single-person to multi-person interactions through a series of innovative designs, whether for daily conversations, intense arguments, or group counting.
These underlying technology breakthroughs directly translate to a leap in productivity. Under the traditional workflow, a team would typically take over three months to complete 50 episodes. With Seko 2.0, the comic drama production cycle can be reduced by 80% to 90%. Seko's comprehensive features make it feasible for independent creators to produce videos in a "one-person crew" model.
- Explore SekoTalk, built on LightX2V and SenseTime's generation model, enabling multi‑person lip‑sync and natural audio‑visual synchronization for videos: http://sekotalk.com/
Adapting to domestic solutions
Multi-episode creation of AI short dramas and comic dramas involves a large number of shots. A single 5-second video requires generating nearly 100,000 tokens, and 10 to 20 shots can result in a total token demand of 1 to 2 million.
To address this challenge, SenseTime has developed Phased DMD Distillation technology, which can significantly reduce the overall cost of multi-episode generation. By combining phased distillation with a Mixture of Experts (MoE) model, it allows different models to specialize in different stages of the generation process, substantially improving overall model capability and efficiency without increasing inference costs.
SenseTime has also open-sourced LightX2V, the industry's first inference framework enabling real-time video generation. Through optimizations such as DiT distillation acceleration, lightweight VAE, and sparse attention, it achieves low-cost real-time video generation. LightX2V can generate a 5-second video on consumer-grade graphics cards in under 5 seconds, significantly outperforming Sora2, which takes several minutes. To date, it has accumulated over 5.3 million downloads and has gained widespread popularity among creators worldwide.
On domestic chip platforms, Seko can achieve generation effects comparable to international chip platforms in similar timeframes. International chip platforms can generate 1.25 seconds of video per second of operation, while domestic chip platforms generate 1.0625 seconds per second. With domestic chip performance improving and ecosystem maturing, this gap is expected to further narrow down.
In the future, SenseTime will also offer domestic solution options for Seko creators, ushering in a low-cost era of AI video creation with extreme cost-performance ratio.
Topping Douyin's AI short drama chart
In the comic and short drama market, Seko has successfully incubated a series of hit shows, including the live-action short drama "Wan Xin Ji", which topped Douyin's AI Short Drama Chart. Works such as "I Built a Doomsday Fortress on the Mountain Top" and "Yin Shen Lu" have also gained widespread attention.
In the high-quality film and television sector, Seko has officially reached a strategic partnership with Yangtze River Film Group, a leading enterprise in the film and television industry. The two parties will jointly explore the integrated innovation of "Generative AI (AIGC) + Film and Television," planning to launch a series of short dramas based on Jingchu cultural and historical stories next year. The two sides will also co-incubate theatrical-level AIGC films, promoting the integration of AI creative tools into professional film and television production processes.
Powered by LightX2V inference framework to enable low‑cost, high-throughput video generation
HONG KONG, Dec. 22, 2025 /PRNewswire/ -- SenseTime launched its Seko 2.0, a multi-episode drama generation agent tailored for short drama and motion comic creators. Supporting production up to 100-episode series, Seko 2.0 ensures consistency in characters, scenes, and props across episodes. It significantly boosts production efficiency, reducing comic drama production time by 80% to 90% compared to traditional methods.
Seko 2.0 is powered by SenseTime's open‑source LightX2V framework, the industry's first inference framework capable of real‑time video generation. This innovative framework allows for cost-effective and high-throughput video production.
Supporting 100-episode series generation
First launched in July 2025, Seko attracted over 100,000 creators within two months and its user base surpassed 200,000 in less than half a year, 30% of which were short drama creators and 20% comic drama creators.
The new Seko 2.0 further lowers the creative threshold and enables more efficient video production. Its key upgraded features include:
- A revamped User Interface (UI) with optimized visual presentation, delivering an immersive creative experience.
- Multi-episode generation capability with long-context management, supporting the creation up to 100 episodes.
- Intelligent Agent scheduling, enabling flexible association of characters, scenes, and props across episodes, with character makeup and styling adaptable to different scenarios.
Xu Li, Chairman of the Board and CEO of SenseTime, stated: "Seko will open a door for people, who have creative imagination, but lack of professional production capabilities, so they can truly enter the creative ecosystem and unleash their imagination." He added that, as AI capabilities continue to evolve, the quality of generated episodes will gradually move up, generating both refined "high-brow" works and popular "low-brow" content that can coexist harmoniously.
AI comic and short dramas have experienced an explosive growth in China. Data shows that the supply of comic dramas in mainland China surged at compound annual growth rate (CAGR) of 83% in the first half of this year. Meanwhile, more than 3,000 works were produced with total revenues jumping by 12 times. Many individual creators and small teams have joined this creative trend, some even taking it as their second career.
Enabling multi-person lip-sync & audio-visual synchronization
Most existing AI video generation products on the market only support single-episode short films or clip production. To meet creators' urgent demand for high-quality, large-scale multi-episode production, Seko 2.0 achieves two core technology breakthroughs:
1) SekoIDX: Achieving character consistency across multi-episode and cross-shot scenarios
Maintaining character consistency across episodes and shots has long been an industry challenge. Traditional generation methods often result in characters appearing as "copied and pasted" (lacking vividness) or "unrecognizable" when responding to new motion or expression promots. By introducing "negative reference images" in the high-noise phase of diffusion models, SekoIDX ensures character consistency across multi-episode and cross-shot content while avoiding excessive similarity to reference images. It also maintains high stability when responding to commands for different expressions, poses, and scenes.
2) SekoTalk: Realizing multi-person lip-sync and natural audio-visual synchronization
Traditional digital human technology often suffers from inaccurate lip-sync in complex scenarios involving multi-language and multi-person interactions. As the industry's first solution supporting lip-sync for more than two people, SekoTalk achieves highly precise audio-visual synchronization from single-person to multi-person interactions through a series of innovative designs, whether for daily conversations, intense arguments, or group counting.
These underlying technology breakthroughs directly translate to a leap in productivity. Under the traditional workflow, a team would typically take over three months to complete 50 episodes. With Seko 2.0, the comic drama production cycle can be reduced by 80% to 90%. Seko's comprehensive features make it feasible for independent creators to produce videos in a "one-person crew" model.
- Explore SekoTalk, built on LightX2V and SenseTime's generation model, enabling multi‑person lip‑sync and natural audio‑visual synchronization for videos: http://sekotalk.com/
Adapting to domestic solutions
Multi-episode creation of AI short dramas and comic dramas involves a large number of shots. A single 5-second video requires generating nearly 100,000 tokens, and 10 to 20 shots can result in a total token demand of 1 to 2 million.
To address this challenge, SenseTime has developed Phased DMD Distillation technology, which can significantly reduce the overall cost of multi-episode generation. By combining phased distillation with a Mixture of Experts (MoE) model, it allows different models to specialize in different stages of the generation process, substantially improving overall model capability and efficiency without increasing inference costs.
SenseTime has also open-sourced LightX2V, the industry's first inference framework enabling real-time video generation. Through optimizations such as DiT distillation acceleration, lightweight VAE, and sparse attention, it achieves low-cost real-time video generation. LightX2V can generate a 5-second video on consumer-grade graphics cards in under 5 seconds, significantly outperforming Sora2, which takes several minutes. To date, it has accumulated over 5.3 million downloads and has gained widespread popularity among creators worldwide.
On domestic chip platforms, Seko can achieve generation effects comparable to international chip platforms in similar timeframes. International chip platforms can generate 1.25 seconds of video per second of operation, while domestic chip platforms generate 1.0625 seconds per second. With domestic chip performance improving and ecosystem maturing, this gap is expected to further narrow down.
In the future, SenseTime will also offer domestic solution options for Seko creators, ushering in a low-cost era of AI video creation with extreme cost-performance ratio.
Topping Douyin's AI short drama chart
In the comic and short drama market, Seko has successfully incubated a series of hit shows, including the live-action short drama "Wan Xin Ji", which topped Douyin's AI Short Drama Chart. Works such as "I Built a Doomsday Fortress on the Mountain Top" and "Yin Shen Lu" have also gained widespread attention.
In the high-quality film and television sector, Seko has officially reached a strategic partnership with Yangtze River Film Group, a leading enterprise in the film and television industry. The two parties will jointly explore the integrated innovation of "Generative AI (AIGC) + Film and Television," planning to launch a series of short dramas based on Jingchu cultural and historical stories next year. The two sides will also co-incubate theatrical-level AIGC films, promoting the integration of AI creative tools into professional film and television production processes.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
SenseTime Launches Seko 2.0 Drama Series Generation Platform
|
VANCOUVER, BC, Dec. 22, 2025 /PRNewswire/ -- Wondershare, a global leader in creative and productivity solutions, today announced a strategic collaboration with Topaz Labs, a pioneer in AI-powered video enhancement. As part of the initial rollout, Topaz's diffusion-driven enhancement model, Starlight, has been integrated into Wondershare's all-in-one AI Video Converter & Enhancer, UniConverter, with plans to expand the integration across additional products—including Wondershare Filmora, Wondershare SelfyzAI, Wondershare Repairit, and more—in future updates. This partnership marks a significant leap in video enhancement performance, giving users access to capabilities traditionally reserved for advanced production pipelines.
The global video production market was valued at $98.99 billion in 2023 and is projected to reach $746.88 billion by 2030, reflecting a rapid 33.5% CAGR. As video creation continues to surge, creators increasingly require higher-fidelity visual outputs across a broader variety of source materials. Wondershare has long been committed to elevating the creative experience by partnering with leading technology innovators. The collaboration with Topaz Labs reflects this commitment and reinforces Wondershare's long-term vision of building a robust, AI-driven creative ecosystem. By bringing advanced AI models into its product lineup, Wondershare aims to provide creators with more powerful and intuitive tools that enhance both the quality and versatility of their content.
Topaz Labs Starlight stands as the world's first diffusion-based AI model for video enhancement and the only solution to deliver full temporal consistency across frames. Through its integration with UniConverter, the tool now offers exceptional detail reconstruction and unifies five key restoration tasks—upscaling, denoising, deblurring, de-aliasing, and sharpening—within a seamless, one-click workflow capable of elevating even sub-480p footage to HD or 4K quality. Powered by cloud-based compute, the process requires no high-end GPU, allowing everyday devices to achieve professional-grade results at speed. From restoring legacy footage and improving low-resolution online videos to clarifying animated linework and upgrading AI-generated materials, UniConverter substantially broadens the range of content creators can enhance, refine, and repurpose.
"Wondershare has always been committed to empowering creators by bringing advanced technologies into accessible, easy-to-use tools," said Sam Zhang, Vice President of Wondershare. "We are delighted to collaborate with Topaz Labs, whose leadership in AI video enhancement aligns closely with our mission. This partnership marks an exciting step forward, and we will continue exploring new collaborations and innovations that help creators produce exceptional content with greater efficiency and confidence."
"For years, Wondershare has been a leader in video editing and production technology," says Dr. Suraj Raghuraman, Head of AI Engine at Topaz Labs. "Much like our team here at Topaz, Wondershare has built a reputation for innovation and quality in their tools, so we're thrilled to partner with them to bring world-class video enhancement to UniConverter, and soon to other Wondershare products as well."
About Wondershare:
Wondershare is a globally recognized software company founded in 2003, known for its innovative solutions in creativity and productivity. Driven by the mission "Creativity Simplified", Wondershare offers a range of tools, including Filmora and SelfyzAI for video editing; PDFelement for document management; and EdrawMax, EdrawMind for diagramming. With over 2 billion cumulative active users across all products and a presence in over 200 countries and regions, Wondershare empowers the next generation of creators with intuitive software and trendy creative resources, continually expanding the possibilities of creativity worldwide.
VANCOUVER, BC, Dec. 22, 2025 /PRNewswire/ -- Wondershare, a global leader in creative and productivity solutions, today announced a strategic collaboration with Topaz Labs, a pioneer in AI-powered video enhancement. As part of the initial rollout, Topaz's diffusion-driven enhancement model, Starlight, has been integrated into Wondershare's all-in-one AI Video Converter & Enhancer, UniConverter, with plans to expand the integration across additional products—including Wondershare Filmora, Wondershare SelfyzAI, Wondershare Repairit, and more—in future updates. This partnership marks a significant leap in video enhancement performance, giving users access to capabilities traditionally reserved for advanced production pipelines.
The global video production market was valued at $98.99 billion in 2023 and is projected to reach $746.88 billion by 2030, reflecting a rapid 33.5% CAGR. As video creation continues to surge, creators increasingly require higher-fidelity visual outputs across a broader variety of source materials. Wondershare has long been committed to elevating the creative experience by partnering with leading technology innovators. The collaboration with Topaz Labs reflects this commitment and reinforces Wondershare's long-term vision of building a robust, AI-driven creative ecosystem. By bringing advanced AI models into its product lineup, Wondershare aims to provide creators with more powerful and intuitive tools that enhance both the quality and versatility of their content.
Topaz Labs Starlight stands as the world's first diffusion-based AI model for video enhancement and the only solution to deliver full temporal consistency across frames. Through its integration with UniConverter, the tool now offers exceptional detail reconstruction and unifies five key restoration tasks—upscaling, denoising, deblurring, de-aliasing, and sharpening—within a seamless, one-click workflow capable of elevating even sub-480p footage to HD or 4K quality. Powered by cloud-based compute, the process requires no high-end GPU, allowing everyday devices to achieve professional-grade results at speed. From restoring legacy footage and improving low-resolution online videos to clarifying animated linework and upgrading AI-generated materials, UniConverter substantially broadens the range of content creators can enhance, refine, and repurpose.
"Wondershare has always been committed to empowering creators by bringing advanced technologies into accessible, easy-to-use tools," said Sam Zhang, Vice President of Wondershare. "We are delighted to collaborate with Topaz Labs, whose leadership in AI video enhancement aligns closely with our mission. This partnership marks an exciting step forward, and we will continue exploring new collaborations and innovations that help creators produce exceptional content with greater efficiency and confidence."
"For years, Wondershare has been a leader in video editing and production technology," says Dr. Suraj Raghuraman, Head of AI Engine at Topaz Labs. "Much like our team here at Topaz, Wondershare has built a reputation for innovation and quality in their tools, so we're thrilled to partner with them to bring world-class video enhancement to UniConverter, and soon to other Wondershare products as well."
About Wondershare:
Wondershare is a globally recognized software company founded in 2003, known for its innovative solutions in creativity and productivity. Driven by the mission "Creativity Simplified", Wondershare offers a range of tools, including Filmora and SelfyzAI for video editing; PDFelement for document management; and EdrawMax, EdrawMind for diagramming. With over 2 billion cumulative active users across all products and a presence in over 200 countries and regions, Wondershare empowers the next generation of creators with intuitive software and trendy creative resources, continually expanding the possibilities of creativity worldwide.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
Wondershare Announces Strategic Collaboration with Topaz Labs to Bring Industry-Leading AI Video Enhancement to Its Creative Software Ecosystem
