Your SuperIntelligence Dealer | NeoCloud | Inference Provider | Agent Cloud | https://xitter.cf/t.co/E5Iqo6HBFP
Spacetime
Joined August 2023
- Tweets1.1K
- Following259
- Followers5.1K
- Likes4.1K
Perceptron.cloud retweeted
🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available!
Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture.
Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene.
Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go.
🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow.
🤖 ModelScope:
modelscope.cn/models/Qwen/Qw…
🤗 Hugging Face:
huggingface.co/Qwen/Qwen-Ima…
🔗 Pro API:
modelstudio.console.alibabac…
🔗 Turbo API:
modelstudio.console.alibabac…
What will you create with 8 steps? Share your results with us!
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨
A unified model for both generation and editing, delivering top-tier quality in a lightweight package.
Highlights: 👀
- Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs.
- Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images.
- Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products.
- Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography.
Start to create your next masterpiece with Qwen-Image-2.1! 🖼️
- Blog: qwen.ai/blog?id=qwen-image-2…
- GitHub: github.com/QwenLM/Qwen-Image…
- Model Scope: modelscope.cn/models/Qwen/Qw…
- Hugging Face: huggingface.co/Qwen/Qwen-Ima…
Perceptron.cloud retweeted
folks, i’m building a game. a very big, beautiful game.
the biggest, most tremendous game you’ve ever seen.
nobody builds games like this, believe me, it's gonna be massive.
it’s gonna be incredible. and i'm building it with SuperIntelligent @perceptroncloud Personas.
we're using this to bringup our new compute cluster, and i'm itching to cook some slop
🤖 Made with AI
Perceptron.cloud retweeted
experimenting with opus 5.5 and deepseek v4.1 flash for motion graphics
it appears opus was post-trained on high quality motion graphics data
here's an attempt at the (in)famous p(doom) music video using deepseek v4.1 flash with @perceptroncloud Studio Vectors
i'm working on making Personas excellent at motion graphics using the Studio skill with more affordable models instead of opus
want to see more experiments? let me know in the comments, i could publish a journal with more results
this video's source code and all generated assets also now ship with the Studio skill on Perceptron, so you can tell your Personas to edit and play with it
Perceptron.cloud retweeted
SpaceX's Starship rocket has successfully reached orbit and deployed its V3 Starlink satellites into orbit for the first time, officially making this Starship's first revenue-generating flight, a major milestone for the company!
Congrats @SpaceX team! Incredible achievement 🚀
Perceptron.cloud retweeted
Starship’s 14th flight is set to launch on Monday, Sept 28. The 75-minute launch window opens at 7:15 a.m. CT. Live coverage of the mission starts ~35 minutes before launch → xitter.cf/i/broadcasts/1qxvvenMP…
