正在加载视频...

视频加载失败

返回首页

🎥 Introducing Hailuo's Subject Reference: Revolutionizing Character Consistency in Video Creation 🔥 We’re excited to present Hailuo's S2V-01 model, a groundbreaking innovation in AI video generation that tackles one of the industry’s biggest challenges: maintaining consistent, realistic facial features and identity across dynamic video content, regardless of camera angles...

Hailuo_AI's profile picture

Hailuo AI (MiniMax)

73,934 subscribers

692,382 次观看 • 1 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

11 条评论

Hailuo AI (MiniMax) 的头像
Hailuo AI (MiniMax)1 年前

reference images

Freepik 的头像
Freepik1 年前

🚀 Introducing Freepik AI video generator. Everything you need to create high-quality, physically accurate videos in one place. 🤩

Apple Dog 的头像
Apple Dog1 年前

The possibilities are endless… amazing🍎🫶

Crack GPT 的头像
Crack GPT1 年前

Also accept me into your artist program 😭🫡

Anna 🌍☮️ 的头像
Anna 🌍☮️1 年前

Bullish on Hailuo and $apple

Nim Eshed 𝕏🦋 的头像
Nim Eshed 𝕏🦋1 年前

Love it

heart 的头像
heart1 年前

Just keeps getting better! 🍎

Nim Eshed 𝕏🦋 的头像
Nim Eshed 𝕏🦋1 年前

Love it so much

David Lemanowicz 的头像
David Lemanowicz1 年前

I think we crashed the site...

ForeverCurtis.Xrp.Bruh🔺ᚱᚹᛟ 的头像
ForeverCurtis.Xrp.Bruh🔺ᚱᚹᛟ1 年前

the only limit is your own imagination! 🍎🐶

Brent Lynch 的头像
Brent Lynch1 年前

It's ON! ;)

相关视频

🚀 Create stunning, character-consistent videos with Hailuo's Subject Reference (S2V-01) Model 🚀: ✨ Single-Image Simplicity: Unlock precise facial details from just one reference image. ⚡ Ultra-Low Cost: Achieve results at less than 1% of traditional computational demands. 🌟 High Flexibility: Enjoy creative freedom with simple text prompts. ⏳ Faster Results: Experience drastically reduced wait times and reliable outputs. Transform your video creation process today! 🎥
0:35

🚀 Create stunning, character-consistent videos with Hailuo's Subject Reference (S2V-01) Model 🚀: ✨ Single-Image Simplicity: Unlock precise facial details from just one reference image. ⚡ Ultra-Low Cost: Achieve results at less than 1% of traditional computational demands. 🌟 High Flexibility: Enjoy creative freedom with simple text prompts. ⏳ Faster Results: Experience drastically reduced wait times and reliable outputs. Transform your video creation process today! 🎥

Hailuo AI (MiniMax)

630,412 次观看 • 1 年前

🔥 New Vidu Update 🔥Multi-Reference Consistency Now you can define a reference subject each with up to 3 images and @ mention it anytime for consistent video generation! 🎥 More stability, more references (up to 7!), and even better anime-style precision.
0:30

🔥 New Vidu Update 🔥Multi-Reference Consistency Now you can define a reference subject each with up to 3 images and @ mention it anytime for consistent video generation! 🎥 More stability, more references (up to 7!), and even better anime-style precision.

Vidu AI

47,503 次观看 • 1 年前

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺
1:00

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

Ideogram

1,712,514 次观看 • 10 个月前

🚨 Consistent Character🚨 Creating videos with consistent characters has never been easier thanks to Hailuo AI (MiniMax) Subject Reference feature in early access. 🎥✨ Just one reference photo is enough to generate videos with perfectly consistent characters. 2025 is already off to an amazing start! 🚀
0:20

🚨 Consistent Character🚨 Creating videos with consistent characters has never been easier thanks to Hailuo AI (MiniMax) Subject Reference feature in early access. 🎥✨ Just one reference photo is enough to generate videos with perfectly consistent characters. 2025 is already off to an amazing start! 🚀

Pierrick Chevallier | IA

21,911 次观看 • 1 年前

Alright, another test with Hailuo AI (MiniMax)'s subject reference and I’m really impressed. 1. The scene starts with the character out of frame and not visible. 2. Once exposed to the scene, it keeps the character consistent. It’s so good.
0:45

Alright, another test with Hailuo AI (MiniMax)'s subject reference and I’m really impressed. 1. The scene starts with the character out of frame and not visible. 2. Once exposed to the scene, it keeps the character consistent. It’s so good.

Halim Alrasihi

31,751 次观看 • 1 年前

Everyone on X has been buzzing about character consistency in 2024. We’re excited to present: multi-character consistency! With a simple workflow, you can easily train custom models that generate multiple consistent characters (2 or more) right from your browser on #Scenario—no complex setup or editing needed. They can take on authentic poses and actions based on a simple prompt. Check out the short video below and more details!
3:41

Everyone on X has been buzzing about character consistency in 2024. We’re excited to present: multi-character consistency! With a simple workflow, you can easily train custom models that generate multiple consistent characters (2 or more) right from your browser on #Scenario—no complex setup or editing needed. They can take on authentic poses and actions based on a simple prompt. Check out the short video below and more details!

Emm | scenario.com

21,410 次观看 • 1 年前

Vidu just launched "Reference to Video" — one of the most exciting features I’ve seen this year. With one actor photo, it generates multi-actor scenes in any setting, solving character consistency almost perfectly, with great quality. 1. the promo video we made for testing:
1:11

Vidu just launched "Reference to Video" — one of the most exciting features I’ve seen this year. With one actor photo, it generates multi-actor scenes in any setting, solving character consistency almost perfectly, with great quality. 1. the promo video we made for testing:

汗青 HQ

46,202 次观看 • 11 个月前

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions! 🎥 Highlights: ✅Subject Consistency: Maintains identity across single & multi-subject video generation. ✅Multimodal Inputs: Supports text, images, audio, and video for highly controlled outputs. ✅High-Quality Output: Industry-leading detail, motion smoothness, and lighting realism. Key Features: 1️⃣Single-Subject Video: Upload an image + text (e.g., “He’s walking a dog”) to create coherent videos with new actions, outfits, and scenes. 2️⃣Multi-Subject Video: Generate videos with multiple subjects (e.g., a man drinking coffee in a cozy room) from separate image inputs. 3️⃣Audio-Driven Video: Sync audio with visuals for talking or singing in any scene—perfect for digital avatars, virtual customer service, and more. 4️⃣Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements. Dive Deeper: 🌐Project: 📝Technical Details: 💻Code: The single-subject video capability is open-sourced and live on the Hunyuan website, with more features to be released soon! 👉 Try it now: #HunyuanCustom #VideoGeneration #AI #TencentHunyuan
0:40

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions! 🎥 Highlights: ✅Subject Consistency: Maintains identity across single & multi-subject video generation. ✅Multimodal Inputs: Supports text, images, audio, and video for highly controlled outputs. ✅High-Quality Output: Industry-leading detail, motion smoothness, and lighting realism. Key Features: 1️⃣Single-Subject Video: Upload an image + text (e.g., “He’s walking a dog”) to create coherent videos with new actions, outfits, and scenes. 2️⃣Multi-Subject Video: Generate videos with multiple subjects (e.g., a man drinking coffee in a cozy room) from separate image inputs. 3️⃣Audio-Driven Video: Sync audio with visuals for talking or singing in any scene—perfect for digital avatars, virtual customer service, and more. 4️⃣Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements. Dive Deeper: 🌐Project: 📝Technical Details: 💻Code: The single-subject video capability is open-sourced and live on the Hunyuan website, with more features to be released soon! 👉 Try it now: #HunyuanCustom #VideoGeneration #AI #TencentHunyuan

Tencent HY

191,908 次观看 • 1 年前

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai
1:15

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

Kōda

155,089 次观看 • 1 个月前

We’re bringing identity consistency to Veo 3.1. For the first time ever, you have complete control of your Veo generations across every voice, character, and scene. With HeyGen’s avatar technology, generate once in Veo 3.1 and your avatar stays consistent, keeping your real voice and true look every time. Voice Consistency: Choose your voice, and HeyGen blends your real tone into Veo’s cinematic motion. Multi-Scene Consistency: Seamless transitions between scenes, one identity, endless stories. Character Consistency: Keep using that avatar with consistent voice and appearance to create unlimited videos in different outfits, styles and environments This is what happens when the world’s best video generator meets the best avatar technology. Don’t just make a scene. Free your story.
1:52

We’re bringing identity consistency to Veo 3.1. For the first time ever, you have complete control of your Veo generations across every voice, character, and scene. With HeyGen’s avatar technology, generate once in Veo 3.1 and your avatar stays consistent, keeping your real voice and true look every time. Voice Consistency: Choose your voice, and HeyGen blends your real tone into Veo’s cinematic motion. Multi-Scene Consistency: Seamless transitions between scenes, one identity, endless stories. Character Consistency: Keep using that avatar with consistent voice and appearance to create unlimited videos in different outfits, styles and environments This is what happens when the world’s best video generator meets the best avatar technology. Don’t just make a scene. Free your story.

HeyGen

1,863,951 次观看 • 8 个月前

Consistent character with Hunyuan and Skyreel! 🎥✨ In collaboration with Kartel.ai .ai, we worked on a pipeline using ComfyUI with the Hunyuan & Skyreel models—both designed for video. We first captured him volumetrically, then trained a LoRA model directly on video data, allowing us to generate sequences where a person remains consistent across shots. The goal is to maintain identity and style over time, pushing the limits of AI-generated video. Excited to explore this further! 🔥 with J. Salvatore in main actor , thank you ! #AI #GenAI #ComfyUI #LoRA #VideoGeneration #Hunyuan #Skyreel
1:28

Consistent character with Hunyuan and Skyreel! 🎥✨ In collaboration with Kartel.ai .ai, we worked on a pipeline using ComfyUI with the Hunyuan & Skyreel models—both designed for video. We first captured him volumetrically, then trained a LoRA model directly on video data, allowing us to generate sequences where a person remains consistent across shots. The goal is to maintain identity and style over time, pushing the limits of AI-generated video. Excited to explore this further! 🔥 with J. Salvatore in main actor , thank you ! #AI #GenAI #ComfyUI #LoRA #VideoGeneration #Hunyuan #Skyreel

Lovis Odin

13,348 次观看 • 1 年前

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇
0:37

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇

ViggleAI

400,233 次观看 • 3 个月前

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation
2:16

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,262 次观看 • 2 年前

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model with Gradio demo local demo: This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. Despite achieving reasonable results, these approaches face challenges in maintaining temporal consistency throughout the animation due to the lack of temporal modeling and poor preservation of reference identity. In this work, we introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity. To achieve this, we first develop a video diffusion model to encode temporal information. Second, to maintain the appearance coherence across frames, we introduce a novel appearance encoder to retain the intricate details of the reference image. Leveraging these two innovations, we further employ a simple video fusion technique to encourage smooth transitions for long video animation. Empirical results demonstrate the superiority of our method over baseline approaches on two benchmarks. Notably, our approach outperforms the strongest baseline by over 38% in terms of video fidelity on the challenging TikTok dancing dataset. Code and model will be made available.
1:15

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model with Gradio demo local demo: This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. Despite achieving reasonable results, these approaches face challenges in maintaining temporal consistency throughout the animation due to the lack of temporal modeling and poor preservation of reference identity. In this work, we introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity. To achieve this, we first develop a video diffusion model to encode temporal information. Second, to maintain the appearance coherence across frames, we introduce a novel appearance encoder to retain the intricate details of the reference image. Leveraging these two innovations, we further employ a simple video fusion technique to encourage smooth transitions for long video animation. Empirical results demonstrate the superiority of our method over baseline approaches on two benchmarks. Notably, our approach outperforms the strongest baseline by over 38% in terms of video fidelity on the challenging TikTok dancing dataset. Code and model will be made available.

AK

810,024 次观看 • 2 年前

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency
0:21

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

AK

31,997 次观看 • 2 年前

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.
0:46

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.

Emm | scenario.com

48,818 次观看 • 1 年前

introducing character consistency for videos. now you can upload the image of a character using Hailuo and preserve their identity in all your videos. try it now!
0:30

introducing character consistency for videos. now you can upload the image of a character using Hailuo and preserve their identity in all your videos. try it now!

Krea

132,247 次观看 • 1 年前

Make Pixels Dance: High-Dynamic Video Generation paper page: Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on text-to-video generation, tend to produce video clips with minimal motions despite maintaining high fidelity. We argue that relying solely on text instructions is insufficient and suboptimal for video generation. In this paper, we introduce PixelDance, a novel approach based on diffusion models that incorporates image instructions for both the first and last frames in conjunction with text instructions for video generation. Comprehensive experimental results demonstrate that PixelDance trained with public data exhibits significantly better proficiency in synthesizing videos with complex scenes and intricate motions, setting a new standard for video generation.
3:09

Make Pixels Dance: High-Dynamic Video Generation paper page: Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on text-to-video generation, tend to produce video clips with minimal motions despite maintaining high fidelity. We argue that relying solely on text instructions is insufficient and suboptimal for video generation. In this paper, we introduce PixelDance, a novel approach based on diffusion models that incorporates image instructions for both the first and last frames in conjunction with text instructions for video generation. Comprehensive experimental results demonstrate that PixelDance trained with public data exhibits significantly better proficiency in synthesizing videos with complex scenes and intricate motions, setting a new standard for video generation.

AK

101,655 次观看 • 2 年前