15s of MiniMax-H3 video + audio, generated in ~72s on one RTX 5090.
Our baseline took ~26 minutes. We wrote up how LightX2V got it down to 72s 👇
768×1344, steady-state benchmark. MP4 export and network transfer excluded.
82103.2K
LightX2V studio✓
@LightX2V
Make something fun with LightX2V ✨🪐 Studio: https://t.co/qEDEa50IEE Discord: https://t.co/RhYdAsdJY6 Github🔍: https://t.co/Pi5qOFuxmz
164 Following49 Followers191 Posts
- POV: When the email is a little too scary to send alone 😂 Made with MiniMax H3 in LightX2V Studio. This one took just 25 seconds to generate ⚡00117
- Your RTX 5090 has a new side quest 👀 Real-time AI video generation with EdenLive 5B, powered by LightX2V. We measured ~24.7 inference FPS at 1280×704 on one card after warmup. Grab the code from the original post, give it a spin, and show us what you build!LightX2V studio @LightX2VLightX2V powers real-time EdenLive on a single RTX 5090 ⚡ Our team built the acceleration that makes this setup possible. 🥳 Proud to play a key role in bringing EdenLive to the community, and big thanks to the VAST team for open-sourcing it! Got an RTX 5090? Grab the code and try EdenLive locally with LightX2V. We’d love to hear how it runs for you! 🙌 👉 Try it with LightX2V: 🌱 Explore EdenLive:00172
- LightX2V powers real-time EdenLive on a single RTX 5090 ⚡ Our team built the acceleration that makes this setup possible. 🥳 Proud to play a key role in bringing EdenLive to the community, and big thanks to the VAST team for open-sourcing it! Got an RTX 5090? Grab the code and try EdenLive locally with LightX2V. We’d love to hear how it runs for you! 🙌 👉 Try it with LightX2V: 🌱 Explore EdenLive:
002144 - “Stay With Me~” hits different under neon lights 🌆🎶 Made with the LightX2V Studio API, combining our singing avatar model with MiniMax-H3 for the story scenes. We handed the script, shot planning, transitions and API calls over to Codex. Turns out making an AI music video can involve a lot less clicking!!! #AIMusicVideo #AIAvatar #LightX2V014279
- ⚡ Meet LightX2V APP — an open-source macOS app for running Qwen-Image-2.1-Turbo locally, with optional Prompt Enhancement. 🛠️ Powered by LightX2V for image generation and llama.cpp for Prompt Enhancement. 🎨 Create images from text, refine them with references, and keep your creations on your Mac. Tested on an M4 Pro with 24GB unified memory. 💻 Download the app, explore the code, and make it your own: #LightX2V #llamacpp #QwenImage #LocalAI #OpenSource #macOS207177
- Less waiting for your AI videos 🙌 Meet LightVAE: up to 4.2× faster VAE decoding for Wan2.1, Wan2.2 and MiniMax-H3. Code, weights and ComfyUI workflows are open source. Give it a spin and let us know how it runs on your setup!Chengtao Lv @mackWilliams319🚀 We're excited to release LightVAE! The first framework to accelerate both video VAE encoding and decoding. ⚡ Up to 4.2× faster VAE decoding! MiniMax-H3 reference-image encoding is also up to 2.68× faster. ✨ Supports Wan2.1, Wan2.2, and MiniMax-H3, with high-fidelity and lightweight variants that largely preserve generation quality. 🧩 Temporal low-rank compression, block pruning, and teacher-guided quality recovery. Code, model weights, and ComfyUI workflows are all open source! 🙌 Check it out and give it a try—we'd love to hear your feedback! 📄 Paper: LightVAE: Towards Compact and Efficient Video Autoencoders 🤗 Model weights: ⭐ Code and ComfyUI workflows:201230
🚀 We're excited to release LightVAE! The first framework to accelerate both video VAE encoding and decoding. ⚡ Up to 4.2× faster VAE decoding! MiniMax-H3 reference-image encoding is also up to 2.68× faster. ✨ Supports Wan2.1, Wan2.2, and MiniMax-H3, with high-fidelity and lightweight variants that largely preserve generation quality. 🧩 Temporal low-rank compression, block pruning, and teacher-guided quality recovery. Code, model weights, and ComfyUI workflows are all open source! 🙌 Check it out and give it a try—we'd love to hear your feedback! 📄 Paper: LightVAE: Towards Compact and Efficient Video Autoencoders 🤗 Model weights: ⭐ Code and ComfyUI workflows:002349- Posts @LightX2V📜Paper: LightVAE: 🤗 Weights: 🔧 Code & ComfyUI workflows:00034
- Tried turning a pet photo into a cartoon with LightX2V Studio’s image-to-image mode and… look at that little face 🥹🐾 Your pet as a comic book character. Who’s trying their cat or dog next?
Sgt Sref @sergeantsref--sref 1857978768 299043543104137 
- Run Qwen-Image-2.1-Turbo locally on your Mac 💻 Here’s what we measured on an Apple M4 Pro with 24GB unified memory, using 8 inference steps: • 512 resolution: 38s total, 3.3s per denoising step • 1K: 118s total, 13.1s per step • 2K: 622s total, 72.7s per step These timings exclude prompt enhancement. In our tests, prompt quality made a big difference, so we recommend keeping enhancement enabled. It adds about a minute via llama.cpp on this setup. Want to try local AI image generation? LightX2V APP runs on Apple Silicon, with Qwen-Image-2.1-Turbo and built-in prompt enhancement: 💫💫Get the Mac app： Building your own workflow? The LightX2V inference framework supports Qwen-Image-2.1 on NVIDIA, AMD, Apple Silicon, and other chips: 💫💫Explore LightX2V： Both repos are open source. 🔥🔥 Give them a try and tell us how they run on your setup. Feedback and contributions are always welcome 🙌306224
- Turn a group image into a conversation with LightX2V Studio.🦋 Give each character a voice. Create in Free Mode or Agent Mode, or build it into your app with the LightX2V Studio API.225103
- AI image generation, right on your Mac 💻 LightX2V APP is here! Run Qwen-Image-2.1-Turbo locally on Apple Silicon, with text-to-image and image-to-image support. Give it a try. Show us what you make 👀 Download LightX2V APP 👇🏻👇🏻👇🏻104100
- Posts @LightX2VRequires Apple Silicon and macOS 14+. Also supports these GGUF Q8_0 prompt enhancement models: • Qwen-Image-2.1-PE-T2I-GGUF-Q8_0 • Qwen-Image-2.1-PE-I2I-GGUF-Q8_0 Start with the Stable download in the README.00165
- Run Qwen-Image-2.1-Turbo locally on your Mac 🍎 LightX2V now supports AI image generation on Apple Silicon via MPS — merged into main. Running it on your Mac? Share your chip, memory, and results. We’d love to hear how it goes. #LightX2V #QwenImage106204
- Posts @LightX2VTry it online now! 🎬 Create with MiniMax H3, Wan 2.2, SekoTalk, Qwen-Image, SwiftVR, and more in LightX2V Studio. No installation needed. Come see what you can make! 👉002108
- Show more posts
