Loading video...

Video Failed to Load

Go Home

Mushroom Headed Skateboarder! 🍄🍄 Made with Seedance 2.0 Fast model though MiniMax Design (H3) #Sundayvibes #Sundaymotivation #SundayThoughts #SundayFunday Good Sunday

JayKay65220066's profile picture

Jay Kay

14,122 subscribers

11,346 views • 3 months ago •via X (Twitter)

#Sundayvibes#Sundaymotivation#SundayThoughts#SundayFunday
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Have a good Sunday morning, everyone! ☕️ Made with Seedance 2.0 model through MiniMax Design (H3) #Sundayvibes #Sundaymotivation #SundayThoughts #SundayFunday
0:15

Have a good Sunday morning, everyone! ☕️ Made with Seedance 2.0 model through MiniMax Design (H3) #Sundayvibes #Sundaymotivation #SundayThoughts #SundayFunday

Jay Kay

14,374 views • 1 month ago

Sand Surfing! 🏜️🏄‍♂️ Made with Kling AI 3.0 Turbo model! #Sundayvibes #Sundaymotivation #SundayThoughts #SundayFunday Good Sunday
0:15

Sand Surfing! 🏜️🏄‍♂️ Made with Kling AI 3.0 Turbo model! #Sundayvibes #Sundaymotivation #SundayThoughts #SundayFunday Good Sunday

Jay Kay

10,602 views • 22 days ago

Barber Shop Mishap! 🧵💈 Made with Seedance 2.0 mini model through MiniMax Design (H3) #Tuesdayvibes #Tuesdaymotivation #TuesdayFeeling #TuesdayFun Good Tuesday
0:15

Barber Shop Mishap! 🧵💈 Made with Seedance 2.0 mini model through MiniMax Design (H3) #Tuesdayvibes #Tuesdaymotivation #TuesdayFeeling #TuesdayFun Good Tuesday

Jay Kay

14,052 views • 2 months ago

This is why silent mode exists🤣 ~ Made with Seedance 2.0 on MiniMax Design (H3)
0:15

This is why silent mode exists🤣 ~ Made with Seedance 2.0 on MiniMax Design (H3)

V𝕩Render

213,049 views • 22 days ago

I compared MiniMax H3 and Seedance 2.0 on Pollo AI using the exact same prompt, and the results were surprisingly different. The output from MiniMax H3 feels noticeably more realistic, with natural motion, authentic facial expressions, and fewer artificial-looking details. MiniMax H3 shows how prompt refinement and model capability can significantly improve AI-generated video quality. What are your thoughts? Which version do you find more realistic?
0:14

I compared MiniMax H3 and Seedance 2.0 on Pollo AI using the exact same prompt, and the results were surprisingly different. The output from MiniMax H3 feels noticeably more realistic, with natural motion, authentic facial expressions, and fewer artificial-looking details. MiniMax H3 shows how prompt refinement and model capability can significantly improve AI-generated video quality. What are your thoughts? Which version do you find more realistic?

Theo

36,206 views • 27 days ago

After running one generation with each model using the same prompt, I compared MiniMax H3 and Seedance 2.5. H3 has a stronger visual sense: its 3D elements feel more current, the pacing is excellent, and the music fits a brand launch perfectly. Seedance 2.5 feels fairly standard, but without H3 as a direct comparison, it still looks pretty good.
0:15

After running one generation with each model using the same prompt, I compared MiniMax H3 and Seedance 2.5. H3 has a stronger visual sense: its 3D elements feel more current, the pacing is excellent, and the music fits a brand launch perfectly. Seedance 2.5 feels fairly standard, but without H3 as a direct comparison, it still looks pretty good.

Amalia

769,381 views • 26 days ago

When the new model drops and your entire workflow turns into pure chaos. 🤯 White cat mascot coding at 3 AM, shark onesie on the couch, a real cat riding an alligator… this is the kind of unhinged creativity that #MiniMaxH3 is about to unlock. Made with MiniMax Design (H3) × MiniMax (official). The future of AI video is going to be wild.
0:15

When the new model drops and your entire workflow turns into pure chaos. 🤯 White cat mascot coding at 3 AM, shark onesie on the couch, a real cat riding an alligator… this is the kind of unhinged creativity that #MiniMaxH3 is about to unlock. Made with MiniMax Design (H3) × MiniMax (official). The future of AI video is going to be wild.

Farhan Ai

10,286 views • 1 month ago

100 AI Styles in 100 Days Day 56/100 📷 Art Style: Stylized 2D hand-painted storybook animation, modern Western animation character design, painterly gouache texture, bold graphic shapes, minimal linework, warm cinematic colors, expressive proportions, handcrafted illustration feel (for Midjourney) 📷A young Greek man saves a princess on the streets of ancient China… but what are they doing here? 👀 Let’s find out in the first trailer. 🎬 Thanks WHORANGE for sharing the --sref 374636695 Made with Seedance 2.0 using a Chinese prompt on MiniMax Design (H3)
0:15

100 AI Styles in 100 Days Day 56/100 📷 Art Style: Stylized 2D hand-painted storybook animation, modern Western animation character design, painterly gouache texture, bold graphic shapes, minimal linework, warm cinematic colors, expressive proportions, handcrafted illustration feel (for Midjourney) 📷A young Greek man saves a princess on the streets of ancient China… but what are they doing here? 👀 Let’s find out in the first trailer. 🎬 Thanks WHORANGE for sharing the --sref 374636695 Made with Seedance 2.0 using a Chinese prompt on MiniMax Design (H3)

ToaiDanh

12,445 views • 17 days ago

you don't need Seedance 2.5, here's cheaper and more efficient workflow we made this entire game shooting scene in one shot for $1.97 with DeepSeek V4 Flash 0731 + MiniMax H3 we use DeepSeek to code the raw Three.js scene first: exact camera movement, character motion, timing, everything. keep tweaking it there for basically pennies. then feed the final footage into H3 and let it cook the realism 48 mins, $1.97 total, one H3 generation way cheaper than rerolling a video model 10 times
0:14

you don't need Seedance 2.5, here's cheaper and more efficient workflow we made this entire game shooting scene in one shot for $1.97 with DeepSeek V4 Flash 0731 + MiniMax H3 we use DeepSeek to code the raw Three.js scene first: exact camera movement, character motion, timing, everything. keep tweaking it there for basically pennies. then feed the final footage into H3 and let it cook the realism 48 mins, $1.97 total, one H3 generation way cheaper than rerolling a video model 10 times

GMI Cloud

157,525 views • 21 days ago

MiniMax H3 is insane. I wanted to see if it could handle a full game-style cinematic, not just one good-looking shot. So I gave it a scene with an ancient water temple, a glowing artifact, a giant stone guardian, and a fast escape sequence. A lot could have gone wrong. The character could have changed. The environment could have broken. The camera could have lost the action. The sound could have felt completely disconnected. But the whole sequence stayed surprisingly consistent. The character, camera movement, water, lighting, action, and audio all felt like they belonged in the same world. It still has small flaws, but this feels much closer to creating a real game cutscene than generating random AI clips. Made with MiniMax H3. Hailuo AI (MiniMax) #MiniMaxH3
0:15

MiniMax H3 is insane. I wanted to see if it could handle a full game-style cinematic, not just one good-looking shot. So I gave it a scene with an ancient water temple, a glowing artifact, a giant stone guardian, and a fast escape sequence. A lot could have gone wrong. The character could have changed. The environment could have broken. The camera could have lost the action. The sound could have felt completely disconnected. But the whole sequence stayed surprisingly consistent. The character, camera movement, water, lighting, action, and audio all felt like they belonged in the same world. It still has small flaws, but this feels much closer to creating a real game cutscene than generating random AI clips. Made with MiniMax H3. Hailuo AI (MiniMax) #MiniMaxH3

Farhan

16,289 views • 29 days ago

This one was made with Seedance 2.0 Fast via Dreamina. This is pure Omni-Reference. The only character sheet I used was for these girls, Sari and Ploy. The dude with sarung here and the location were 100% prompted. I didn’t use a character sheet or reference for either of them. Even in Fast mode, Seedance 2.0 is bloody good and it still nails the hyper-vernacular vibe that I always aim for in my work. Seedance 2.0 is both exciting and scary for me 😆 It’s exciting because it is undoubtedly the best model currently available on the market. Trust me, you’ve seen the videos I’ve made so far right? The performance of the model It’s simply the best, period. It has helped me tremendously in creating a shit ton of stories about the region where I live, Southeast Asia. It has been the most exciting thing ever. The scary part is whenever a platform or company comes to me saying, “Hey, we have this new video model. Blah blah blah. We’ll let you know more soon.” It scares the shit out of me because the big question is whether it will be better than Seedance 2.0??? 😆😆 If not, I don’t even want to bother using it. I’ve come this far and achieved this level of quality with Seedance 2.0. That’s why I skipped Happy Horse, which I already tested. It’s also why I’m not bothering with Wan or anything else for now. Their current models are still far inferior to what we already get with Seedance 2.0. I don’t want to downgrade the visual quality. This is also why I need to be really honest. There are certain platforms that host their own in-house models and i'm still part of their CPP. However, because those models are still far behind the quality of Seedance 2.0, I haven’t used them that much. Seedance 2.0 has simply become the benchmark for me. The type of output I’m looking for is also extremely specific, so I can immediately feel it when a model cannot deliver what I need. Seedance 2.0 is definitely not cheap, but it gives me so much creative satisfaction and allows me to make whatever I want. I even have a team that low-key makes softcore erotic videos in the style of Vivamax 😆 I think I’ve trimmed down so many things in my AI workflow because my main goal is to focus on the content itself. If Seedance 2.0 Mini is released soon, I’m dead curious to test it. I think I want to create more stories that revolve around drama rather than highly technical cinematic shots. Seedance 2.0 Fast has been incredibly helpful, but I’m definitely curious to check out the Mini version. But the truth is that I’m completely tool-agnostic. I don’t care which company makes the model. I only care about the quality. You might remember when I praised Grok Imagine Video so damn hard because it was genuinely amazing back then. Then the quality kept getting worse and worse, so I stopped using it. But if it gets better again, I’ll definitely want to use it again. At the end of the day, quality is the only thing that matters.
0:15

This one was made with Seedance 2.0 Fast via Dreamina. This is pure Omni-Reference. The only character sheet I used was for these girls, Sari and Ploy. The dude with sarung here and the location were 100% prompted. I didn’t use a character sheet or reference for either of them. Even in Fast mode, Seedance 2.0 is bloody good and it still nails the hyper-vernacular vibe that I always aim for in my work. Seedance 2.0 is both exciting and scary for me 😆 It’s exciting because it is undoubtedly the best model currently available on the market. Trust me, you’ve seen the videos I’ve made so far right? The performance of the model It’s simply the best, period. It has helped me tremendously in creating a shit ton of stories about the region where I live, Southeast Asia. It has been the most exciting thing ever. The scary part is whenever a platform or company comes to me saying, “Hey, we have this new video model. Blah blah blah. We’ll let you know more soon.” It scares the shit out of me because the big question is whether it will be better than Seedance 2.0??? 😆😆 If not, I don’t even want to bother using it. I’ve come this far and achieved this level of quality with Seedance 2.0. That’s why I skipped Happy Horse, which I already tested. It’s also why I’m not bothering with Wan or anything else for now. Their current models are still far inferior to what we already get with Seedance 2.0. I don’t want to downgrade the visual quality. This is also why I need to be really honest. There are certain platforms that host their own in-house models and i'm still part of their CPP. However, because those models are still far behind the quality of Seedance 2.0, I haven’t used them that much. Seedance 2.0 has simply become the benchmark for me. The type of output I’m looking for is also extremely specific, so I can immediately feel it when a model cannot deliver what I need. Seedance 2.0 is definitely not cheap, but it gives me so much creative satisfaction and allows me to make whatever I want. I even have a team that low-key makes softcore erotic videos in the style of Vivamax 😆 I think I’ve trimmed down so many things in my AI workflow because my main goal is to focus on the content itself. If Seedance 2.0 Mini is released soon, I’m dead curious to test it. I think I want to create more stories that revolve around drama rather than highly technical cinematic shots. Seedance 2.0 Fast has been incredibly helpful, but I’m definitely curious to check out the Mini version. But the truth is that I’m completely tool-agnostic. I don’t care which company makes the model. I only care about the quality. You might remember when I praised Grok Imagine Video so damn hard because it was genuinely amazing back then. Then the quality kept getting worse and worse, so I stopped using it. But if it gets better again, I’ll definitely want to use it again. At the end of the day, quality is the only thing that matters.

MXVDXN // DAN

18,949 views • 2 months ago

I topped up $5 on an API aggregator ToAPIs Then I found out GPT Image 2 costs only around $0.015 per image. If you do a lot of testing or batch-generate commercial AI images, that difference adds up fast. I think I just found the secret to generating more, testing more, and spending less. And it’s not just one model. With the same key, you can access 50+ models for image, video, and text, including GPT Image 2, Gemini Omni, Seedance 2.0, Kling AI 3.0, grok-video-1.5-preview, and more. Some models are priced up to 80% lower than official platforms. Just top up and test what you need: Made on ToAPIs with GPT Image 2 + Seedance 2.0
0:15

I topped up $5 on an API aggregator ToAPIs Then I found out GPT Image 2 costs only around $0.015 per image. If you do a lot of testing or batch-generate commercial AI images, that difference adds up fast. I think I just found the secret to generating more, testing more, and spending less. And it’s not just one model. With the same key, you can access 50+ models for image, video, and text, including GPT Image 2, Gemini Omni, Seedance 2.0, Kling AI 3.0, grok-video-1.5-preview, and more. Some models are priced up to 80% lower than official platforms. Just top up and test what you need: Made on ToAPIs with GPT Image 2 + Seedance 2.0

Shami

22,991 views • 2 months ago

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B MoE refresh, Terminal-Bench 2.1 jumps 61.8→82.7 over the preview, DeepSWE 7.3→54.4. Closes in on Opus-4.8 on Agents' Last Exam (25.2 vs 25.7). MIT. → Muse-Glimmer-30B, from Meta (they are back!!): their first open agentic model. ~29.6B dense + perception encoder, 131k+ context, built to run fully local, no cloud. Apache 2.0. → Liquid AI LFM2.5-2.6B: 2.69B params, 131k context, 220 tok/s on an M5 Max in under 2.5GB RAM. Competitive with models 4x larger on agentic tasks. → inclusionAI Ling-3.0-flash: 124B total, only 5.1B active, ~12% the size of their old 1T flagship Ring-2.6, matches it on key benchmarks. MIT. → inclusionAI Ling-3.0-tiny: 7.9B total, 1.3B active, 86-90 tok/s on an M4 Pro MacBook at ~8GB peak memory. MIT. → NVIDIA Nemotron-3.5-Lightning-30B-A3B: hybrid Mamba-2+MoE+Attention, up to 1M context, runs on a single H100 or DGX Spark, SWE-bench Verified 52.8. → deepgrove maple-preview: 20B-A1B ternary-weight reasoner, 218 tok/s on a Mac mini M4, 5.3GB checkpoint. MIT. → BigBang-v1 (endless-frontier): fine-tuned from Qwen3.6-35B-A3B via a self-evolving generator/critic synthetic-data loop. Lands aggregate performance between DeepSeek V4 Flash (284B) and V4 Pro (1.6T), at 35B. Apache 2.0. 🎬 Video → MiniMax-H3: 33B dense omni model, native stereo audio, up to 2K/15s. 3.6k+ likes already. → Minimax-H3-Turbo (lightx2v): Apache-2.0 turbo distillation of H3 for fast inference. → Lightricks LTX-2.5: image-to-video update, custom Gemma-4-12B text encoder, a markedly stronger distilled model. 🔊 Voice → NVIDIA NemotronLabs VoiceChat-11B: full-duplex speech-to-speech, ~450ms turn-taking, #2 on open VoiceBench, and the first open full-duplex model with live tool-calling mid-conversation. 🛡️ Safety → Mistral Shieldstral-1.0-3B: 3B multimodal guardrail that takes your safety policy as plain text instead of fixed categories. Beats LlamaGuard-4-12B and ShieldGemma-9B on HarmBench (99.4) and ToxicChat (84.1) at a fraction of the size. Apache 2.0.
0:14

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B MoE refresh, Terminal-Bench 2.1 jumps 61.8→82.7 over the preview, DeepSWE 7.3→54.4. Closes in on Opus-4.8 on Agents' Last Exam (25.2 vs 25.7). MIT. → Muse-Glimmer-30B, from Meta (they are back!!): their first open agentic model. ~29.6B dense + perception encoder, 131k+ context, built to run fully local, no cloud. Apache 2.0. → Liquid AI LFM2.5-2.6B: 2.69B params, 131k context, 220 tok/s on an M5 Max in under 2.5GB RAM. Competitive with models 4x larger on agentic tasks. → inclusionAI Ling-3.0-flash: 124B total, only 5.1B active, ~12% the size of their old 1T flagship Ring-2.6, matches it on key benchmarks. MIT. → inclusionAI Ling-3.0-tiny: 7.9B total, 1.3B active, 86-90 tok/s on an M4 Pro MacBook at ~8GB peak memory. MIT. → NVIDIA Nemotron-3.5-Lightning-30B-A3B: hybrid Mamba-2+MoE+Attention, up to 1M context, runs on a single H100 or DGX Spark, SWE-bench Verified 52.8. → deepgrove maple-preview: 20B-A1B ternary-weight reasoner, 218 tok/s on a Mac mini M4, 5.3GB checkpoint. MIT. → BigBang-v1 (endless-frontier): fine-tuned from Qwen3.6-35B-A3B via a self-evolving generator/critic synthetic-data loop. Lands aggregate performance between DeepSeek V4 Flash (284B) and V4 Pro (1.6T), at 35B. Apache 2.0. 🎬 Video → MiniMax-H3: 33B dense omni model, native stereo audio, up to 2K/15s. 3.6k+ likes already. → Minimax-H3-Turbo (lightx2v): Apache-2.0 turbo distillation of H3 for fast inference. → Lightricks LTX-2.5: image-to-video update, custom Gemma-4-12B text encoder, a markedly stronger distilled model. 🔊 Voice → NVIDIA NemotronLabs VoiceChat-11B: full-duplex speech-to-speech, ~450ms turn-taking, #2 on open VoiceBench, and the first open full-duplex model with live tool-calling mid-conversation. 🛡️ Safety → Mistral Shieldstral-1.0-3B: 3B multimodal guardrail that takes your safety policy as plain text instead of fixed categories. Beats LlamaGuard-4-12B and ShieldGemma-9B on HarmBench (99.4) and ToxicChat (84.1) at a fraction of the size. Apache 2.0.

Victor M

54,264 views • 19 days ago

The Future of AI Filmmaking Starts Here with MiniMax H3 MiniMax Design (H3) #MiniMaxH3 Try here : Model: MiniMax H3 Aspect Ratio: 3:4 Resolution: 2K Prompt: Create a 40-second Hollywood-style cinematic film teaser for a sci-fi thriller titled "THE LAST SIGNAL." Scene 1: A lone astronaut walks across an abandoned lunar research station under a dark sky. Dust floats in slow motion. One red emergency light flashes. Ultra-realistic, IMAX quality, volumetric lighting. Scene 2: Deep underground, scientists discover an ancient metallic object buried beneath ice. Strange glowing symbols slowly activate. Cinematic camera push-in. Scene 3: A mysterious signal begins spreading across satellites surrounding Earth. Massive orbital structures light up simultaneously. Scene 4: Cities worldwide lose power. Giant holographic waves move through skyscrapers. Rain, smoke, emergency vehicles, cinematic chaos. Scene 5: A female scientist stares at thousands of floating holographic equations while whispering, "It's communicating." Scene 6: A colossal alien structure slowly rises from the ocean during sunrise. Enormous scale, cinematic drone shot. Scene 7: Fast montage: • fighter jets • exploding satellites • astronauts floating in zero gravity • underground bunker • frightened child looking at the sky • giant alien silhouette inside storm clouds Final Scene: The screen fades to black. Title appears: THE LAST SIGNAL Tagline: "They were never gone." Coming Soon. Style: Hollywood blockbuster, Denis Villeneuve-inspired cinematic language, ultra-realistic, 8K, anamorphic lenses, dramatic contrast, volumetric fog, realistic skin, global illumination, HDR, dynamic camera movement, cinematic color grading, premium VFX, emotionally intense pacing, realistic physics, Dolby-style atmosphere, epic scale.
0:15

The Future of AI Filmmaking Starts Here with MiniMax H3 MiniMax Design (H3) #MiniMaxH3 Try here : Model: MiniMax H3 Aspect Ratio: 3:4 Resolution: 2K Prompt: Create a 40-second Hollywood-style cinematic film teaser for a sci-fi thriller titled "THE LAST SIGNAL." Scene 1: A lone astronaut walks across an abandoned lunar research station under a dark sky. Dust floats in slow motion. One red emergency light flashes. Ultra-realistic, IMAX quality, volumetric lighting. Scene 2: Deep underground, scientists discover an ancient metallic object buried beneath ice. Strange glowing symbols slowly activate. Cinematic camera push-in. Scene 3: A mysterious signal begins spreading across satellites surrounding Earth. Massive orbital structures light up simultaneously. Scene 4: Cities worldwide lose power. Giant holographic waves move through skyscrapers. Rain, smoke, emergency vehicles, cinematic chaos. Scene 5: A female scientist stares at thousands of floating holographic equations while whispering, "It's communicating." Scene 6: A colossal alien structure slowly rises from the ocean during sunrise. Enormous scale, cinematic drone shot. Scene 7: Fast montage: • fighter jets • exploding satellites • astronauts floating in zero gravity • underground bunker • frightened child looking at the sky • giant alien silhouette inside storm clouds Final Scene: The screen fades to black. Title appears: THE LAST SIGNAL Tagline: "They were never gone." Coming Soon. Style: Hollywood blockbuster, Denis Villeneuve-inspired cinematic language, ultra-realistic, 8K, anamorphic lenses, dramatic contrast, volumetric fog, realistic skin, global illumination, HDR, dynamic camera movement, cinematic color grading, premium VFX, emotionally intense pacing, realistic physics, Dolby-style atmosphere, epic scale.

Mr Farman Ai

14,175 views • 1 month ago

Classic Michael moment with H3. Prompt below 👇 The Office & Kim Jong Un. 0:00–0:04 — Medium-wide shot inside the Dunder Mifflin office. Michael Scott walks in with open arms and an enormous forced smile, guiding a completely expressionless Kim Jong Un in his black suit. Michael enthusiastically says: “Welcome, my good friend, to the greatest paper company on Earth!” 0:04–0:08 — Michael points around the office with wild hand gestures: “This is Jim’s desk, that’s Pam’s, and over there is Dwight’s weird little kingdom…” Kim just stares in absolute silence, eyes narrowing slightly. 0:08–0:12 — Michael leans in way too close, still smiling awkwardly: “And this conference room… this is where I once declared bankruptcy. Classic Michael moment!” He laughs alone. Kim remains completely still. 0:12–0:15 — Michael, completely misreading the silence, suddenly goes for a big enthusiastic hug. Kim’s face fills with pure cold rage, eyes locked on Michael like a death sentence. The video ends abruptly on Kim’s terrifying stare while Michael freezes mid-hug. I've just used a couple of image references for this one! Hope you like it. Made it in MiniMax Design (H3) !
0:15

Classic Michael moment with H3. Prompt below 👇 The Office & Kim Jong Un. 0:00–0:04 — Medium-wide shot inside the Dunder Mifflin office. Michael Scott walks in with open arms and an enormous forced smile, guiding a completely expressionless Kim Jong Un in his black suit. Michael enthusiastically says: “Welcome, my good friend, to the greatest paper company on Earth!” 0:04–0:08 — Michael points around the office with wild hand gestures: “This is Jim’s desk, that’s Pam’s, and over there is Dwight’s weird little kingdom…” Kim just stares in absolute silence, eyes narrowing slightly. 0:08–0:12 — Michael leans in way too close, still smiling awkwardly: “And this conference room… this is where I once declared bankruptcy. Classic Michael moment!” He laughs alone. Kim remains completely still. 0:12–0:15 — Michael, completely misreading the silence, suddenly goes for a big enthusiastic hug. Kim’s face fills with pure cold rage, eyes locked on Michael like a death sentence. The video ends abruptly on Kim’s terrifying stare while Michael freezes mid-hug. I've just used a couple of image references for this one! Hope you like it. Made it in MiniMax Design (H3) !

TechHalla

69,671 views • 27 days ago

made with seedance 2.0 fast on LumeFlow AI Official Prompt, 15-Second Cinematic Skincare Ad Prompt Prompt: Create a luxurious 15-second skincare commercial featuring a beautiful young woman promoting "LUMINA GLOW Brightening Face Wash." Elegant bathroom setting with soft natural sunlight, warm tones, premium beauty-commercial aesthetics, glowing skin, shallow depth of field, smooth cinematic camera movements, realistic facial expressions, high-end skincare advertisement, ultra-realistic, 4K quality. Scene Breakdown: 0-2s: Model holds the LUMINA GLOW Face Wash and smiles at the camera. Product displayed prominently. Text: "Cleanse • Refresh • Glow." 2-4s: Close-up of her applying the face wash to her cheeks and forehead. Soft lighting highlights healthy skin. 4-7s: She gently massages the product into a rich creamy lather. Slow-motion beauty shots, detailed foam texture. 7-9s: Model rinses her face with clear water. Water splashes captured in cinematic slow motion. 9-11s: She dries her face with a white towel, revealing fresh, clean, radiant skin. 11-13s: Close-up beauty shot showcasing glowing, smooth, hydrated skin. Natural smile and confidence. 13-15s: Hero product shot on a premium countertop with flowers and soft bokeh background. Brand logo appears with slogan: "LUMINA GLOW – Let Your Natural Glow Shine." Style Keywords: Luxury skincare commercial, beauty ad, cinematic lighting, realistic skin texture, premium cosmetics marketing, elegant female model, smooth transitions, commercial-grade production, soft glow effect, photorealistic, 4K, high detail, advertising quality, vertical social media ad.
0:15

made with seedance 2.0 fast on LumeFlow AI Official Prompt, 15-Second Cinematic Skincare Ad Prompt Prompt: Create a luxurious 15-second skincare commercial featuring a beautiful young woman promoting "LUMINA GLOW Brightening Face Wash." Elegant bathroom setting with soft natural sunlight, warm tones, premium beauty-commercial aesthetics, glowing skin, shallow depth of field, smooth cinematic camera movements, realistic facial expressions, high-end skincare advertisement, ultra-realistic, 4K quality. Scene Breakdown: 0-2s: Model holds the LUMINA GLOW Face Wash and smiles at the camera. Product displayed prominently. Text: "Cleanse • Refresh • Glow." 2-4s: Close-up of her applying the face wash to her cheeks and forehead. Soft lighting highlights healthy skin. 4-7s: She gently massages the product into a rich creamy lather. Slow-motion beauty shots, detailed foam texture. 7-9s: Model rinses her face with clear water. Water splashes captured in cinematic slow motion. 9-11s: She dries her face with a white towel, revealing fresh, clean, radiant skin. 11-13s: Close-up beauty shot showcasing glowing, smooth, hydrated skin. Natural smile and confidence. 13-15s: Hero product shot on a premium countertop with flowers and soft bokeh background. Brand logo appears with slogan: "LUMINA GLOW – Let Your Natural Glow Shine." Style Keywords: Luxury skincare commercial, beauty ad, cinematic lighting, realistic skin texture, premium cosmetics marketing, elegant female model, smooth transitions, commercial-grade production, soft glow effect, photorealistic, 4K, high detail, advertising quality, vertical social media ad.

Zyro

108,732 views • 1 month ago

Made this premium FILA style fashion ad using Seedance 2.0. No voiceover,just cinematic visuals, studio lighting, and clean transitions. ✨ PROMPT: Create a 15-second high energy luxury fashion commercial featuring a stylish young woman wearing a white, black, and red color block FILA puffer jacket with a high stand collar, front zipper, quilted padding, and iconic chest logo. Film inside a premium fashion studio with a clean white seamless backdrop, professional softbox lighting, dramatic rim lights, and subtle haze for cinematic depth. Shot on ARRI Alexa 35, Cooke Anamorphic lenses, ultra-realistic 4K HDR, 120fps slow motion for selected moments, crisp editorial color grading, shallow depth of field, premium sportswear campaign aesthetic. Sequence 0–2 sec Rapid macro cuts of the jacket: Close-up of the FILA logo Zipper being pulled up Puffy quilted texture Sleeve color blocking Light gliding across the fabric 2–5 sec The model throws the jacket onto her shoulders in one fluid motion, then quickly zips it up. Fast dolly push-in with dynamic lighting transitions. 5–8 sec Confident runway walk toward the camera. Quick alternating shots: Full-body tracking shot Low-angle hero shot Side profile Close-up of the jacket moving naturally 8–12 sec Quick fashion poses: Adjusting the collar Hands in pockets Looking over the shoulder Half spin Slow-motion hair movement Camera circles around the model 12–15 sec Hero ending. The model stops in the center of the studio, confidently facing the camera. Slow push-in as the jacket fills the frame. End with a clean luxury brand reveal and space for the FILA logo. Style Luxury sportswear campaign, modern streetwear fashion, premium studio production, Vogue editorial, energetic editing, fast-paced cuts every 0.5–1 second, cinematic lighting, ultra-realistic fabric texture, dramatic highlights, smooth gimbal movement, subtle handheld energy, premium commercial quality, stylish, youthful, confident, visually striking. Audio Modern upbeat electronic instrumental with cinematic bass and rhythmic beats. No voiceover. No dialogue. No ambient sounds. No subtitles. Music synchronized with every fast cut for maximum impact.
0:15

Made this premium FILA style fashion ad using Seedance 2.0. No voiceover,just cinematic visuals, studio lighting, and clean transitions. ✨ PROMPT: Create a 15-second high energy luxury fashion commercial featuring a stylish young woman wearing a white, black, and red color block FILA puffer jacket with a high stand collar, front zipper, quilted padding, and iconic chest logo. Film inside a premium fashion studio with a clean white seamless backdrop, professional softbox lighting, dramatic rim lights, and subtle haze for cinematic depth. Shot on ARRI Alexa 35, Cooke Anamorphic lenses, ultra-realistic 4K HDR, 120fps slow motion for selected moments, crisp editorial color grading, shallow depth of field, premium sportswear campaign aesthetic. Sequence 0–2 sec Rapid macro cuts of the jacket: Close-up of the FILA logo Zipper being pulled up Puffy quilted texture Sleeve color blocking Light gliding across the fabric 2–5 sec The model throws the jacket onto her shoulders in one fluid motion, then quickly zips it up. Fast dolly push-in with dynamic lighting transitions. 5–8 sec Confident runway walk toward the camera. Quick alternating shots: Full-body tracking shot Low-angle hero shot Side profile Close-up of the jacket moving naturally 8–12 sec Quick fashion poses: Adjusting the collar Hands in pockets Looking over the shoulder Half spin Slow-motion hair movement Camera circles around the model 12–15 sec Hero ending. The model stops in the center of the studio, confidently facing the camera. Slow push-in as the jacket fills the frame. End with a clean luxury brand reveal and space for the FILA logo. Style Luxury sportswear campaign, modern streetwear fashion, premium studio production, Vogue editorial, energetic editing, fast-paced cuts every 0.5–1 second, cinematic lighting, ultra-realistic fabric texture, dramatic highlights, smooth gimbal movement, subtle handheld energy, premium commercial quality, stylish, youthful, confident, visually striking. Audio Modern upbeat electronic instrumental with cinematic bass and rhythmic beats. No voiceover. No dialogue. No ambient sounds. No subtitles. Music synchronized with every fast cut for maximum impact.

Sophia

65,501 views • 1 month ago

Morning coffee good vibes and a little dance to start the day. ☕ Made with Seedance 2.0 Prompt: A beautifully rendered 3D animated scene in a cozy, sun-drenched apartment kitchen, Pixar style. A young woman with brown hair tied in a messy high bun, wearing a white tank top and white denim shorts, is enjoying her morning. Warm morning sunlight streams through a large window, creating soft lens flares and a golden glow. She is holding a white coffee mug, smiling happily, and lightly dancing or swaying to music. The kitchen features modern countertops, an espresso machine pouring coffee, wooden cutting boards, and subtle kitchen decor. High-quality 3D animation, Disney aesthetics, smooth character movement, vibrant colors, warm lighting, architectural details, 4k resolution.Pixar style 3D animation of a happy young woman in a white tank top and denim shorts dancing in her sunny apartment kitchen. She has a high bun hair style, holds a coffee mug, and smiles warmly. Bright golden hour sunlight coming through the window, cozy interior design, cinematic lighting, ultra-smooth motion.
0:13

Morning coffee good vibes and a little dance to start the day. ☕ Made with Seedance 2.0 Prompt: A beautifully rendered 3D animated scene in a cozy, sun-drenched apartment kitchen, Pixar style. A young woman with brown hair tied in a messy high bun, wearing a white tank top and white denim shorts, is enjoying her morning. Warm morning sunlight streams through a large window, creating soft lens flares and a golden glow. She is holding a white coffee mug, smiling happily, and lightly dancing or swaying to music. The kitchen features modern countertops, an espresso machine pouring coffee, wooden cutting boards, and subtle kitchen decor. High-quality 3D animation, Disney aesthetics, smooth character movement, vibrant colors, warm lighting, architectural details, 4k resolution.Pixar style 3D animation of a happy young woman in a white tank top and denim shorts dancing in her sunny apartment kitchen. She has a high bun hair style, holds a coffee mug, and smiles warmly. Bright golden hour sunlight coming through the window, cozy interior design, cinematic lighting, ultra-smooth motion.

Zyrella

15,298 views • 1 month ago

Who said travel outfits can't steal the spotlight? ✈️🔥 Created with GPT image 2 and Seedance 2.0 on Thank You AI PROMPT: Style: Fast-paced, cinematic, luxury fashion, IMAX-quality visuals, dramatic lighting, premium color grading, energetic editing, no dialogue, powerful electronic trailer music with cinematic impacts. 0:00–0:02 Ultra-wide shot of automatic airport doors sliding open. The model steps in wearing sunglasses and headphones. Quick bass hit. 0:02–0:04 Fast tracking shot from the side as she confidently walks through the terminal, pulling a sleek carry-on. Motion blur and speed ramps. 0:04–0:06 Rapid montage: . Coffee picked up from a café . Boarding pass flips into her hand . Close-up of a luxury watch . Sneakers hitting the polished floor (0.5-second cuts) 0:06–0:09 Low-angle hero shot. She walks through the terminal as sunlight streams through massive windows. People blur past while she stays perfectly in focus. 0:09–0:11 Fast sequence: . Escalator ride . Airport departure board . Hair flip . Adjusts sunglasses . Camera orbit transition 0:11–0:13 Slow motion for a split second as she walks toward the boarding gate. Cinematic lens flares, dramatic trailer boom. 0:13–0:15 Final hero shot from behind as she walks through the jet bridge. She glances back over her shoulder for one frame before the screen cuts to black with a powerful cinematic impact sound. Editing Style . 0.3–1 second shots . Speed ramps . Whip pans . Match cuts . Flash-frame transitions . Bass drops synchronized with cuts . Cinematic trailer pacing . Confident runway-style walk throughout . No dialogue, only high-energy trailer music and cinematic sound design This will feel more like a Netflix action trailer meets a luxury fashion campaign rather than a typical airport vlog.
0:15

Who said travel outfits can't steal the spotlight? ✈️🔥 Created with GPT image 2 and Seedance 2.0 on Thank You AI PROMPT: Style: Fast-paced, cinematic, luxury fashion, IMAX-quality visuals, dramatic lighting, premium color grading, energetic editing, no dialogue, powerful electronic trailer music with cinematic impacts. 0:00–0:02 Ultra-wide shot of automatic airport doors sliding open. The model steps in wearing sunglasses and headphones. Quick bass hit. 0:02–0:04 Fast tracking shot from the side as she confidently walks through the terminal, pulling a sleek carry-on. Motion blur and speed ramps. 0:04–0:06 Rapid montage: . Coffee picked up from a café . Boarding pass flips into her hand . Close-up of a luxury watch . Sneakers hitting the polished floor (0.5-second cuts) 0:06–0:09 Low-angle hero shot. She walks through the terminal as sunlight streams through massive windows. People blur past while she stays perfectly in focus. 0:09–0:11 Fast sequence: . Escalator ride . Airport departure board . Hair flip . Adjusts sunglasses . Camera orbit transition 0:11–0:13 Slow motion for a split second as she walks toward the boarding gate. Cinematic lens flares, dramatic trailer boom. 0:13–0:15 Final hero shot from behind as she walks through the jet bridge. She glances back over her shoulder for one frame before the screen cuts to black with a powerful cinematic impact sound. Editing Style . 0.3–1 second shots . Speed ramps . Whip pans . Match cuts . Flash-frame transitions . Bass drops synchronized with cuts . Cinematic trailer pacing . Confident runway-style walk throughout . No dialogue, only high-energy trailer music and cinematic sound design This will feel more like a Netflix action trailer meets a luxury fashion campaign rather than a typical airport vlog.

Sophia

40,153 views • 29 days ago

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑
0:11

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Vercel Developers

948,088 views • 13 days ago