正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

This feels less like ""AI image generation"" and more like actually directing a shot. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started with a real photo and used GPT-6 Astra + Blender to recreate it as a clay-style scene. Then I used Seedance... show more

Enzo Sanchez | IA

58,920 subscribers

56,485 次观看 • 7 天前 •via X (Twitter)

艺术音乐科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Astra codes the geometry → Blender → Clay Renderer Plugin → final render on Dreamina. The interesting part? You’re not asking AI to guess the scene from scratch. Blender locks the geometry, camera & layout — then Seedance 2.5 takes over to add the final look. One workflow: • Astra builds the geometry • Blender becomes the source of truth • Clay Renderer Plugin sends it to Dreamina • Seedance 2.5 turns it into finished footage Both Seedance 2.5 & Seedance 2.0 at the most competitive price. Try it now 👇 #Dreamina #DreaminaPartner

Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Astra codes the geometry → Blender → Clay Renderer Plugin → final render on Dreamina. The interesting part? You’re not asking AI to guess the scene from scratch. Blender locks the geometry, camera & layout — then Seedance 2.5 takes over to add the final look. One workflow: • Astra builds the geometry • Blender becomes the source of truth • Clay Renderer Plugin sends it to Dreamina • Seedance 2.5 turns it into finished footage Both Seedance 2.5 & Seedance 2.0 at the most competitive price. Try it now 👇 #Dreamina #DreaminaPartner

kamran Hassan

36,160 次观看 • 11 天前

This is a pretty clever way to build AI video. GPT-6 Astra creates the geometry → Blender keeps the camera and layout locked → Dreamina’s Clay Renderer Plugin sends the clay model into Dreamina → Seedance 2.5 turns it into finished footage. The important part is that Seedance isn’t guessing the scene from scratch. Your geometry, camera, and composition are already set. Seedance 2.5 focuses on adding the final look. And both Seedance 2.5 & 2.0 are available at the most competitive price. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Try it now 👇 #Dreamina #DreaminaPartner

This is a pretty clever way to build AI video. GPT-6 Astra creates the geometry → Blender keeps the camera and layout locked → Dreamina’s Clay Renderer Plugin sends the clay model into Dreamina → Seedance 2.5 turns it into finished footage. The important part is that Seedance isn’t guessing the scene from scratch. Your geometry, camera, and composition are already set. Seedance 2.5 focuses on adding the final look. And both Seedance 2.5 & 2.0 are available at the most competitive price. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Try it now 👇 #Dreamina #DreaminaPartner

Nayeem Sheikh

28,279 次观看 • 11 天前

Wait… why did nobody tell me AI-generated posters could go back into an actual Photoshop workflow? Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I generated a poster in Dreamina first, then sent it to GPT-6 Astra. Astra used Photoshop to break the image apart into separate layers, so I could finally adjust the background, typography, and individual elements instead of being stuck with one flat image. For designers, this feels like a missing step between AI generation and professional editing. And because Dreamina keeps the creation cost competitive, I can test multiple poster ideas before deciding which one deserves a full edit. This workflow is kind of a game changer for rapid design exploration. #Dreamina #DreaminaPartner

Wait… why did nobody tell me AI-generated posters could go back into an actual Photoshop workflow? Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I generated a poster in Dreamina first, then sent it to GPT-6 Astra. Astra used Photoshop to break the image apart into separate layers, so I could finally adjust the background, typography, and individual elements instead of being stuck with one flat image. For designers, this feels like a missing step between AI generation and professional editing. And because Dreamina keeps the creation cost competitive, I can test multiple poster ideas before deciding which one deserves a full edit. This workflow is kind of a game changer for rapid design exploration. #Dreamina #DreaminaPartner

Katherine

80,449 次观看 • 6 天前

This is probably the closest I've gotten to going from ""rough idea"" → ""actual product"" without touching a traditional design workflow. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I made the initial product draft in Dreamina, then gave it to GPT-6 Astra. Astra took the visual direction, generated the realistic product, and turned the result into a clean product detail page. Dreamina being cost-efficient makes the first stage even better - I can test multiple product concepts before committing to one. Pretty wild how short the path is now. #Dreamina #DreaminaPartner

This is probably the closest I've gotten to going from ""rough idea"" → ""actual product"" without touching a traditional design workflow. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I made the initial product draft in Dreamina, then gave it to GPT-6 Astra. Astra took the visual direction, generated the realistic product, and turned the result into a clean product detail page. Dreamina being cost-efficient makes the first stage even better - I can test multiple product concepts before committing to one. Pretty wild how short the path is now. #Dreamina #DreaminaPartner

Alif Khan

93,841 次观看 • 7 天前

I honestly didn’t expect this part of the AI design workflow to work this smoothly. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started by creating a poster concept in Dreamina. The image looked finished, but I wanted to edit the individual elements instead of recreating everything. So I gave the poster to GPT-6 Astra and had it call Photoshop to separate the design into editable layers — background, text, objects, and visual elements all became independent pieces. This is the part that surprised me: AI doesn’t just help make the design anymore, it can help turn the final image back into a real design file. Dreamina makes exploring different poster concepts much easier with its competitive pricing, then Astra helps take them into the editing stage. #Dreamina #DreaminaPartner

I honestly didn’t expect this part of the AI design workflow to work this smoothly. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started by creating a poster concept in Dreamina. The image looked finished, but I wanted to edit the individual elements instead of recreating everything. So I gave the poster to GPT-6 Astra and had it call Photoshop to separate the design into editable layers — background, text, objects, and visual elements all became independent pieces. This is the part that surprised me: AI doesn’t just help make the design anymore, it can help turn the final image back into a real design file. Dreamina makes exploring different poster concepts much easier with its competitive pricing, then Astra helps take them into the editing stage. #Dreamina #DreaminaPartner

Vipin Gautam (Viipin I Gautam)

45,029 次观看 • 6 天前

Finally tested the GPT-6 Astra → Blender → Flova workflow. Started with a simple idea, turned it into a clay-style 3D model with GPT-6 Astra, refined it in Blender, then pushed it into Flova for the final render. The clay model was fun to make. But seeing the final render come together was the part that l genuinely blew me away. This workflow has way more potential than I expected. Definitely trying it with more ideas. 🔥

Finally tested the GPT-6 Astra → Blender → Flova workflow. Started with a simple idea, turned it into a clay-style 3D model with GPT-6 Astra, refined it in Blender, then pushed it into Flova for the final render. The clay model was fun to make. But seeing the final render come together was the part that l genuinely blew me away. This workflow has way more potential than I expected. Definitely trying it with more ideas. 🔥

Aryan Rakib

39,516 次观看 • 10 天前

Wait… this is AI animation? The short film 《AKUMA》 from Dreamina × Annecy honestly caught my attention because it feels less like a random generated clip and more like a scene someone actually directed. The prison wagon setup has such a strong mood. The warm light coming through the bars, the rough wood, the small chain rattles, and that subtle wagon movement all make the scene feel alive without doing too much. What I liked most is Saku’s reaction when he wakes up. It is quiet and controlled. He does not panic. He just checks his bandages, looks around, then notices the shackles on his hands. That small acting choice makes the moment feel much more real. The camera also keeps it simple, which works. Close shots, readable faces, little cuts between the characters, and just enough movement to remind you the wagon is still rolling. That is why Dreamina feels interesting to me. Dreamina Octo helps shape the idea and creative direction, while Seedance 2.0 brings it into motion with mood, character acting, and atmosphere. Dreamina AI → Dreamina Octo Creative Agent + Dreamina Seedance 2.0 Animation Model. Dreamina AI #DreaminaAtAnnecy #MadeWithDreamina #AnimationFilm #DreaminaAI

Wait… this is AI animation? The short film 《AKUMA》 from Dreamina × Annecy honestly caught my attention because it feels less like a random generated clip and more like a scene someone actually directed. The prison wagon setup has such a strong mood. The warm light coming through the bars, the rough wood, the small chain rattles, and that subtle wagon movement all make the scene feel alive without doing too much. What I liked most is Saku’s reaction when he wakes up. It is quiet and controlled. He does not panic. He just checks his bandages, looks around, then notices the shackles on his hands. That small acting choice makes the moment feel much more real. The camera also keeps it simple, which works. Close shots, readable faces, little cuts between the characters, and just enough movement to remind you the wagon is still rolling. That is why Dreamina feels interesting to me. Dreamina Octo helps shape the idea and creative direction, while Seedance 2.0 brings it into motion with mood, character acting, and atmosphere. Dreamina AI → Dreamina Octo Creative Agent + Dreamina Seedance 2.0 Animation Model. Dreamina AI #DreaminaAtAnnecy #MadeWithDreamina #AnimationFilm #DreaminaAI

Marry claire

14,091 次观看 • 2 个月前

Seedance 2.5 is making its global-first debut on Dreamina. As an official ByteDance product, it brings a much more flexible workflow for creators: → Up to 50 reference materials → Up to 30 seconds per generation → Local / region-based editing → 3D white model generation → Green screen functionality The part I find most interesting is being able to move from images to video without switching platforms, while Dreamina positions Seedance 2.5 at the lowest price available across the market. And during the 7-day global exclusive launch, Seedance 2.5 is only available on Dreamina. Try it on Dreamina: #dreamina #dreaminapartner #seedance #dreaminaScenes25

Seedance 2.5 is making its global-first debut on Dreamina. As an official ByteDance product, it brings a much more flexible workflow for creators: → Up to 50 reference materials → Up to 30 seconds per generation → Local / region-based editing → 3D white model generation → Green screen functionality The part I find most interesting is being able to move from images to video without switching platforms, while Dreamina positions Seedance 2.5 at the lowest price available across the market. And during the 7-day global exclusive launch, Seedance 2.5 is only available on Dreamina. Try it on Dreamina: #dreamina #dreaminapartner #seedance #dreaminaScenes25

Sanchoy Hossain

382,684 次观看 • 1 个月前

I think people are still underestimating how important the 3D layer could become in AI video. The problem with complex AI shots has never just been image quality. It’s spatial consistency, camera direction and knowing where everything is supposed to be. GPT-6 Astra can map the scene and keep camera + character paths within the Viewport, giving the shot a spatial structure before generation. I then manually move that scene into CapCut PC and use Seedance 2.5 to render it. From there, CapCut PC becomes the actual editing environment. That feels less like “AI generated a video” and more like a production pipeline worth experimenting with. #CapCutPC #GPT6Astra #AIVideo #Seedance25

I think people are still underestimating how important the 3D layer could become in AI video. The problem with complex AI shots has never just been image quality. It’s spatial consistency, camera direction and knowing where everything is supposed to be. GPT-6 Astra can map the scene and keep camera + character paths within the Viewport, giving the shot a spatial structure before generation. I then manually move that scene into CapCut PC and use Seedance 2.5 to render it. From there, CapCut PC becomes the actual editing environment. That feels less like “AI generated a video” and more like a production pipeline worth experimenting with. #CapCutPC #GPT6Astra #AIVideo #Seedance25

Manish Kumar Shah

30,785 次观看 • 11 天前

1/ We've all been aware of the hype surrounding Dreamina Seedance 2.0, and I finally got early access to the tool. And wow, I'm blown away. This is by far the best. It is starting to make AI video feel less like "generate a clip" and more like "direct a scene." What stood out to me is the level of control: camera motion, pacing, visual consistency, and the ability to build from multiple references inside one workflow. Some of the prompt directions that feel especially strong: - a busy modern city square during daytime. Suddenly, time freezes completely - a single continuous camera movement through a natural landscape that transitions through all four seasons in one shot - an underwater bioluminescent city waking up at dawn The big shift is this: One Prompt, Viral Remade. Edit Videos as Easy as Editing Photos. Dreamina Seedance 2.0 feels like a real step toward AI-native directing rather than just AI generation. Here are some examples 🧵:

1/ We've all been aware of the hype surrounding Dreamina Seedance 2.0, and I finally got early access to the tool. And wow, I'm blown away. This is by far the best. It is starting to make AI video feel less like "generate a clip" and more like "direct a scene." What stood out to me is the level of control: camera motion, pacing, visual consistency, and the ability to build from multiple references inside one workflow. Some of the prompt directions that feel especially strong: - a busy modern city square during daytime. Suddenly, time freezes completely - a single continuous camera movement through a natural landscape that transitions through all four seasons in one shot - an underwater bioluminescent city waking up at dawn The big shift is this: One Prompt, Viral Remade. Edit Videos as Easy as Editing Photos. Dreamina Seedance 2.0 feels like a real step toward AI-native directing rather than just AI generation. Here are some examples 🧵:

Chubby♨️

76,557 次观看 • 5 个月前

Dreamina Seedance 2.5 is already here and Dreamina might be the best place to use it. Not just because you can access it early. Dreamina offers the lowest pricing across the entire Seedance suite, making it one of the most affordable ways to create with Seedance 2.5. I tested it today. And after seeing what changed, this feels like a serious leap toward professional AI filmmaking. Here’s what stood out 🧵

Dreamina Seedance 2.5 is already here and Dreamina might be the best place to use it. Not just because you can access it early. Dreamina offers the lowest pricing across the entire Seedance suite, making it one of the most affordable ways to create with Seedance 2.5. I tested it today. And after seeing what changed, this feels like a serious leap toward professional AI filmmaking. Here’s what stood out 🧵

Md Riyazuddin

153,252 次观看 • 1 个月前

Dreamina Seedance 2.5 is officially live globally (yes, including the US) right on Dreamina - offering the full Seedance lineup at the absolute lowest price on the market. ByteDance just pushed the limits of AI video generation once again. Dreamina is actually the very first platform on the planet to roll out Seedance 2.5. This is far more than just a standard model update. It is a massive leap towards true professional AI filmmaking. Here is exactly what makes it stand out 👇

Dreamina Seedance 2.5 is officially live globally (yes, including the US) right on Dreamina - offering the full Seedance lineup at the absolute lowest price on the market. ByteDance just pushed the limits of AI video generation once again. Dreamina is actually the very first platform on the planet to roll out Seedance 2.5. This is far more than just a standard model update. It is a massive leap towards true professional AI filmmaking. Here is exactly what makes it stand out 👇

Oluwatimileyin✨🦋

37,238 次观看 • 1 个月前

Seedance 2.0 - Test Demo 04 I used one image I generated back in 2024 by MJ V5 to Seedance S2.0. This image style is mixed with 80s animation and 70s illustration. Wanna check how Seedance 2.0 can handle the mocap for this style? And here is the result. #seedance2 Dreamina AI Midjourney

Seedance 2.0 - Test Demo 04 I used one image I generated back in 2024 by MJ V5 to Seedance S2.0. This image style is mixed with 80s animation and 70s illustration. Wanna check how Seedance 2.0 can handle the mocap for this style? And here is the result. #seedance2 Dreamina AI Midjourney

Jim HuiHui

32,394 次观看 • 7 个月前

The future of AI video creation is almost here. ByteDance's Dreamina Seedance 2.5 is coming soon, launching globally first on the Dreamina platform. Since Dreamina Seedance 2.5 hasn't launched yet, I created this video using Dreamina Seedance 2.0 to preview what's coming next. Here's what makes Dreamina Seedance 2.5 exciting: ✅ Omni Reference: Support for up to 50 reference assets, including images, videos, and audio, for more accurate and controllable video creation. ✅ 30-Second AI Videos: Generate up to 30 seconds of continuous, consistent storytelling in a single clip. ✅ Professional Editing: Fine-grained refinements, timestamp-based editing, and green screen support for greater creative control. ✅ Multilingual Creation: Create videos in 10+ languages with native language support. Workflow: AI Video → Dreamina Seedance 2.5 → Omni Reference → Upload images, videos & audio → Enter your prompt → Generate Whether you're a content creator, marketer, designer, or filmmaker, Dreamina Seedance 2.5 is shaping up to be one of the most exciting AI video launches of the year. Learn more and get ready for Dreamina Seedance 2.5: #dreamina #dreaminapartner #seedance #dreaminaseedance25

The future of AI video creation is almost here. ByteDance's Dreamina Seedance 2.5 is coming soon, launching globally first on the Dreamina platform. Since Dreamina Seedance 2.5 hasn't launched yet, I created this video using Dreamina Seedance 2.0 to preview what's coming next. Here's what makes Dreamina Seedance 2.5 exciting: ✅ Omni Reference: Support for up to 50 reference assets, including images, videos, and audio, for more accurate and controllable video creation. ✅ 30-Second AI Videos: Generate up to 30 seconds of continuous, consistent storytelling in a single clip. ✅ Professional Editing: Fine-grained refinements, timestamp-based editing, and green screen support for greater creative control. ✅ Multilingual Creation: Create videos in 10+ languages with native language support. Workflow: AI Video → Dreamina Seedance 2.5 → Omni Reference → Upload images, videos & audio → Enter your prompt → Generate Whether you're a content creator, marketer, designer, or filmmaker, Dreamina Seedance 2.5 is shaping up to be one of the most exciting AI video launches of the year. Learn more and get ready for Dreamina Seedance 2.5: #dreamina #dreaminapartner #seedance #dreaminaseedance25

Manish Kumar Shah

62,793 次观看 • 1 个月前

AI video is getting better at generating impressive clips. But I think the more interesting question is how much control you have before the first frame is generated. I’ve been testing a GPT-6 Astra + Seedance 2.5 workflow where the process starts with a 3D scene and spatial planning, rather than just a prompt. Then I manually bring the scene into CapCut PC, use Seedance 2.5 to render it, and finish the video there. Maybe AI filmmaking is moving from “generate something cool” to actually directing the shot. #CapCutPC #GPT6Astra #AIVideo #Seedance25

AI video is getting better at generating impressive clips. But I think the more interesting question is how much control you have before the first frame is generated. I’ve been testing a GPT-6 Astra + Seedance 2.5 workflow where the process starts with a 3D scene and spatial planning, rather than just a prompt. Then I manually bring the scene into CapCut PC, use Seedance 2.5 to render it, and finish the video there. Maybe AI filmmaking is moving from “generate something cool” to actually directing the shot. #CapCutPC #GPT6Astra #AIVideo #Seedance25

Katherine

77,799 次观看 • 11 天前

Dreamina Seedance 2.0 Mini is officially live in the US and now available globally. US users can get 55% off membership plans, plus nearly 50% lower credit costs for Dreamina Seedance 2.0 Mini. This offer is available only in the US. I saved a ton of AI video credits by changing ONE setting. Dreamina Seedance 2.0 Mini looks surprisingly close to the flagship model, Dreamina Seedance 2.0, but it uses significantly fewer credits, making it a much more cost effective option. This underwater exploration scene cost me way less than I expected. 👇 #dreamina #dreaminapartner #seedance #dreaminaseedance2mini

Dreamina Seedance 2.0 Mini is officially live in the US and now available globally. US users can get 55% off membership plans, plus nearly 50% lower credit costs for Dreamina Seedance 2.0 Mini. This offer is available only in the US. I saved a ton of AI video credits by changing ONE setting. Dreamina Seedance 2.0 Mini looks surprisingly close to the flagship model, Dreamina Seedance 2.0, but it uses significantly fewer credits, making it a much more cost effective option. This underwater exploration scene cost me way less than I expected. 👇 #dreamina #dreaminapartner #seedance #dreaminaseedance2mini

SANI BULA

83,515 次观看 • 2 个月前

The next leap in AI video isn't just better visuals. It's having far more control over how those videos are created. Dreamina Seedance 2.5 is coming soon to the Dreamina platform, and what stands out isn't only the quality it's the workflow built around creators. Here's what's coming: • Multimodal input — combine up to 50 reference assets in a single generation. • Longer video generation — create continuous videos of up to 30 seconds. • Structured control — use white-model and green-screen references for more predictable results. • Multilingual creation — build content for international audiences with localization support. • Targeted refinement — edit specific parts of a video instead of regenerating the entire scene. These upgrades make Dreamina Seedance 2.5 feel less like another prompt-to-video model and more like a complete, controllable AI video production pipeline. Learn more: #dreamina #dreaminapartner #seedance #dreaminaseedance25

The next leap in AI video isn't just better visuals. It's having far more control over how those videos are created. Dreamina Seedance 2.5 is coming soon to the Dreamina platform, and what stands out isn't only the quality it's the workflow built around creators. Here's what's coming: • Multimodal input — combine up to 50 reference assets in a single generation. • Longer video generation — create continuous videos of up to 30 seconds. • Structured control — use white-model and green-screen references for more predictable results. • Multilingual creation — build content for international audiences with localization support. • Targeted refinement — edit specific parts of a video instead of regenerating the entire scene. These upgrades make Dreamina Seedance 2.5 feel less like another prompt-to-video model and more like a complete, controllable AI video production pipeline. Learn more: #dreamina #dreaminapartner #seedance #dreaminaseedance25

Md Riyazuddin

33,164 次观看 • 1 个月前

Dreamina has unveiled the world-first global launch of Dreamina Seedance 2.5 - with early access live on Dreamina and US availability expected roughly one week later. For AI marketing teams, the question is no longer: “Can AI generate a video?” We already know it can. The real question is: “Can one workflow turn a single campaign brief into enough consistent variations to actually ship?” With up to 50 multimodal references, 30-second single-generation video, and the lowest-cost access to the full Seedance family, Dreamina is the most cost-effective place to put that workflow to the test.

Dreamina has unveiled the world-first global launch of Dreamina Seedance 2.5 - with early access live on Dreamina and US availability expected roughly one week later. For AI marketing teams, the question is no longer: “Can AI generate a video?” We already know it can. The real question is: “Can one workflow turn a single campaign brief into enough consistent variations to actually ship?” With up to 50 multimodal references, 30-second single-generation video, and the lowest-cost access to the full Seedance family, Dreamina is the most cost-effective place to put that workflow to the test.

Chidanand Tripathi

166,609 次观看 • 1 个月前

A single impressive AI video is a demo. A real production workflow needs much more: Enough references to define the creative direction. Enough duration to complete the shot. Enough control to revise what doesn’t work. Dreamina has unveiled the world-first global launch of Dreamina Seedance 2.5, with early access already live on Dreamina and US availability expected roughly one week later. With up to 50 multimodal references, 30-second single-generation video, and the lowest-cost access to the full Seedance family, Dreamina is the most cost-effective place to move from “generate something interesting” to “build something usable.”

A single impressive AI video is a demo. A real production workflow needs much more: Enough references to define the creative direction. Enough duration to complete the shot. Enough control to revise what doesn’t work. Dreamina has unveiled the world-first global launch of Dreamina Seedance 2.5, with early access already live on Dreamina and US availability expected roughly one week later. With up to 50 multimodal references, 30-second single-generation video, and the lowest-cost access to the full Seedance family, Dreamina is the most cost-effective place to move from “generate something interesting” to “build something usable.”

D-Coder

39,817 次观看 • 1 个月前

Two product images can go surprisingly far. I generated two visuals for a product with GPT Image 2.5, then used them as the starting point for a commercial video in CapCut. GPT Image 2.5 is coming to CapCut, with access through Design Studio and AI Image. The interesting part is what happens next. Instead of treating the images as the final assets, I can move from product visuals into Seedance 2.5 video generation and build out the commercial inside CapCut PC. One product. A couple of visuals. A complete ad workflow. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Two product images can go surprisingly far. I generated two visuals for a product with GPT Image 2.5, then used them as the starting point for a commercial video in CapCut. GPT Image 2.5 is coming to CapCut, with access through Design Studio and AI Image. The interesting part is what happens next. Instead of treating the images as the final assets, I can move from product visuals into Seedance 2.5 video generation and build out the commercial inside CapCut PC. One product. A couple of visuals. A complete ad workflow. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Katyayani Shukla

93,741 次观看 • 4 天前