Knuckle (@Knuckle0001) header
Knuckle (@Knuckle0001) profile picture

Passionate about AI | Design | UI/UX | Web & Mobile Development.

Joined April 2010
Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)Photo by Knuckle (@Knuckle0001)
Knuckle retweeted
完整教程: Higgsfield 动画团队教你怎样把 AI 放进传统动画流程 best.xiaohu.ai/article/higgs…
115
485
22
2,973
163,178
The Kitchen team and Sir Pancake has landed in Tokyo 🛬🇯🇵 See you soon.
PancakeSwap is heading to WebX 2025 in Tokyo! 🇯🇵 Catch us at our booth for special edition pancakes, exclusive merch, and a chance to meet Sir Pancake. Chef Kids (@Headchef_pcs) will also be live on stage talking about RWA liquidity. 🎟️ Come meet us: webx-asia.com/ticket/
32
38
1
153
52,054
Introducing Kontext Relight! 💡 ✨ A FLUX Kontext Relight LoRA + demo trained for state-of-the art relighting for subjects & landscapes
22
82
9
656
76,200
🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference code, data pipelines, and architecture—yours to fine-tune! ✅ Runs on consumer GPUs, empowering creators, devs, and small teams. Be the first to shape the future of 3D! Download now and build something epic. Model: huggingface.co/tencent/Hunyu… Demo: huggingface.co/spaces/tencen… Github: github.com/Tencent-Hunyuan/H… Hunyuan 3D Creation Engine: 3d.hunyuan.tencent.com/ #Hunyuan3D #OpenSource #3DCreation
81
298
59
1,669
236,567
Today we're releasing FLUX.1 Kontext - a suite of generative flow matching models that allow you to generate and edit images. Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing.
166
404
152
2,566
487,798
Knuckle retweeted
StarVector official app is out on Hugging Face Generating Scalable Vector Graphics Code from Images and Text
22
193
15
1,723
167,224
RF-DETR:开源最佳实时识别模型 实时识别画面中的物体,准确率和速度优于YOLO系列模型,开源可商用。 官方介绍:blog.roboflow.com/rf-detr/ Github:github.com/roboflow/rf-detr
9
227
4
896
93,028
全球知名投资机构 @a16z 正式宣布 MCP 市场分析,并正式将这波 MCP 从技术热推广到资本热💥 MCP 正加速从技术协议迈向商业变现,并催收新的面向 AI Agent 的技术栈和生态系统 报告原文 👉 a16z.com/a-deep-dive-into-mc…
5
95
6
363
41,348
太强了!MCP 开始起飞了🛫 有推上老哥开源了一个基于 Cursor 操作 Figma 的 MCP 🔥 直接 Cursor 写代码转成 figma 设计稿.... 还开源了 🤯 地址见评论👇
29
159
5
930
136,242
Interesting
MCP is going crazy viral right now🤯 AI apps can now instantly connect to any tool or live data. USB-C moment for AI. 10 wild examples:
24
DeepSeek R1 + 深度研究 + Ollama 新玩法: 下载Ollama Deep Researcher,在本机装好 R1 。 然后给 R1 一个主题,观察它搜索网络、学习、反思、搜索更多内容。 它会自动重复此过程, 想让它研究多久,它就研究多久。 最后它会给出一份研究彻底的报告,报告附有它看过的所有信息来源。 该项目和模型全部开源。
22
330
10
1,407
243,457
love it!
This is KITSUNE - a tale of love between two souls. 🦊 💫 Written, created and directed by @henrydaubrez. All shots generated with Veo 2 using VideoFX. Watch with sound on. 🔊
1
27
The result look amazing, can’t wait to try it with comfyui
I am truly honored to announce that our 3D open source project has entered its 2.0 version, presenting revolutionary effects that rival those of commercial products. huggingface.co/tencent/Hunyu… github.com/tencent/Hunyuan3D…
3
88
Wow, that 2D drawing animation video was absolutely incredible! I’m so impressed with the way it followed the video reference.
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
1
72
Wow, imagine what we can do about this tracking mark!!
Google Veo 2 VFX Test. Compositing AI generated footage with human created assets will have more applications. Veo 2 obeying to photogrammetry makes 3D camera tracking possible. Instructing your characters to performing in front of green screen for chroma keying, VFX studios can reuse their traditional workflow for post-production. #veo2 #vfx #sakura
30
This looks great, I sincerely hope this tool can handle text in products well
🎥 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 or movements. 💡 Why It’s a Game Changer: - Pioneering Technology: The first-of-its-kind to ensure character consistency in dynamic video generation, surpassing even fine-tuned models in performance. - Minimal Input, Maximum Impact: Generate character-consistent videos from just one reference image. Every frame remains true to the original identity with unmatched accuracy and reliability. - Enhanced Flexibility: Adjust more than just facial features—modify posture, expressions, lighting, and more, all with simple text-based prompts. 🌟While the new model enhances subject consistency, it may occasionally follow prompts less precisely than T2V or I2V, with some environmental morphing. Despite these early-stage challenges, Hailuo Subject Reference marks a significant leap in AI video generation. We’re committed to continual improvements including multi-subject references, objects references, and complex, multi-layered scenes. Explore the future of creative, consistent video production with Hailuo S2V-01 today. 🔥We believe the possibilities are endless.
19
Wow, motion capture based on webcam video can be exported to 3D software, but I wonder how accurate it can be 🧐
AGI Mocap software webcam video dance Blender real-time motion capture #Mocap #Blender #Dance #DiMocap (Send email to [email protected] get a trial version) AGI Mocap: dimocap.com/en/
41
上手实测gemini-2.0一周感想,一个key能顶五六个AI应用。 不同于贵到肉疼的 o1 API, 也区别于“升级版封号斗罗pro-max-plus-ultra”的 Claude(额度是上午充的,号是中午没的。。。) Gemini 它免费啊! 原生多模态能做很多事了,翻译、编程、日常对话、联网搜索、中文视频聊天、视频剪辑、屏幕共享,把我其他AI应用的活也抢了。 这次来总结一下这几个玩法: (1/7)
22
190
8
885
210,487
New model 🤩, sadly it not able to run on commercial grade GPU
🎄Happy holidays and we wish you enjoy this year. Before moving to 2025, Qwen has the last gift for you, which is QVQ! 🎉 This may be the first open-weight model for visual reasoning. It is called QVQ, where V stands for vision. It just reads an image and an instruction, starts thinking, reflects while it should, keeps reasoning, and finally it generates its prediction with confidence! However, it is still experimental and this preview version still suffers from a number of limitations (mentioned in our blog), which you should pay attention to while using the model. Feel free to refer to the following links for more information: * Blog: qwenlm.github.io/blog/qvq-72… * HF: huggingface.co/collections/Q… * ModelScope: modelscope.cn/models/Qwen/QV… * Kaggle: kaggle.com/models/qwen-lm/qv… 🚀 It achieves impressive performance in benchmark evaluation, e.g., MMMU, MathVista, etc. But what is more interesting is that it is exciting to see the AI model behaves differently by thinking deeply and reasoning step by step instead of directly providing answers. Yet, it is still a model for preview. It is unstable, it might fall into repetition, it sometimes doesn't follow instruction, etc. We invite you to try the new interesting model and enjoy playing with it! Feel free to shoot us feedback!
24
正在寻找假期可以尝试的AI产品吗? 以下是来自 a16z 团队和公司朋友的推荐 ⬇️
5
55
2
242
74,856