🤖 Vibe coding with LLMs + prompt craft 🖼️ Curating: AI 📰 Tech ⚡ Security — Best of X. Follow 💙 ♻️
Joined January 2022
- Tweets8.4K
- Following608
- Followers2.7K
- Likes46.3K
AlexAImaginator retweeted
Strata 0.2.0 is now live in beta! It includes its own in-app harness and terminal-serving interface.
github.com/Niko1221/Strata
A lot of performance improvements and support for low-end devices 👇
AlexAImaginator retweeted
xitter.cf/StrataLLM - Crypto Scam. Don't fall for it.
I would never charge you for Strata, as it's open-source.
AlexAImaginator retweeted
Let's try again! I had no luck with previous release.
Hey everyone,
We've updated our FLUX 3 Image Klein workflows to fix some issues and help you get the best results from the model.
• Update to @ComfyUI v0.41.3 and use our updated workflow, link in thread.
• We've updated the @huggingface Space as well.
To get the best results, the model should be used with our prompt upsampling and 2K resolutions.
If you can’t use our prompt upsampling, we’ve also made the recommended system prompt available in our repo to use in your workflows.
Thank you for the feedback everyone!
AlexAImaginator retweeted
🤗 MOSS-Image is now open source on @huggingface .
Built on a 5B Diffusion Transformer (DiT), MOSS-Image brings Chinese & English text rendering and controllable layouts to image generation — from posters and infographics to creative visuals.@Open_MOSS
What it offers:
📝 Long prompts & text rendering — up to 4K-token prompts, including multi-line text
📐 Experimental JSON layout control — specify text, objects, and their positions using bounding boxes
🖼️ Flexible generation — multiple aspect ratios, resolutions, and customizable inference settings 🛠️ Developer workflows — Python (Diffusers), Gradio, ComfyUI, and a Prompt Enhancer Skill
📦 Base & SFT checkpoints are both available, with open model weights and Apache-2.0 licensed inference code.
🙌 Huge thanks to @sgl_project @vllm_project @ModelScope2022 for the Day-0 support!
AlexAImaginator retweeted
Krea 3 by @krea_ai is now in ComfyUI via Partner Nodes.
Reference-driven image gen + editing, built for fast iteration:
→ Multi-reference inputs, addressed by upload order (person from image 1, jacket from image 2)
→ Targeted edits that hold labels, shapes, and materials
→ Swap a fabric or finish in place, same angle, same room
→ Feed results back in and keep going
Faster and cheaper per image, so the third edit is as easy as the first.
AlexAImaginator retweeted
FLUX 3 Image Klein is here.
Open Weights with the quality of a large frontier model. Customizable and fast.
5.6B parameters and runs on a single consumer GPU.
Native 4K, bounding boxes, and pixel-perfect editing.
AlexAImaginator retweeted
Many people saying Strata vibe coded… of course I’m going to use Claude, Codex and Deepseek. How else would I push 3 versions a day and +30% improvements version over version? 🤝
Architecture, logic and good understanding is still needed to achieve that 🫡
See more 👇
AlexAImaginator retweeted
Ming Image 0.1 Design is now available in ComfyUI !
huge thanks to Kijai!
huggingface.co/Kijai/Ming-Im…
Impressive gift for UI/UX designers!
Ming-Image Design - 6B open-source T2I for UI, infographics, posters & text-rich designs;
- full compositions with RGBA transparent backgrounds
- pairs with Design-Layer for editable transparent layer decomp;
- 2048 x 2048
+ VLM prompt enhancer.
huggingface.co/inclusionAI/M…
AlexAImaginator retweeted
We’re open-sourcing the Ming-Image-0.1-Design family:
• Ming-Image-0.1-Design, 6B
• Ming-Image-0.1-Design-Layer, 6B
• Two open-source Agent Skills: the Ling UI Design Skill and the Image-to-Editable-PPT Skill
Ming-Image-0.1-Design ranks #1 among open-weight models on Artificial Analysis’s UI/UX Design leaderboard. 🧵
AlexAImaginator retweeted
Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! 🖼️
The 7B model performs on par with Nano Banana 2.0.
For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.
GGUF: huggingface.co/unsloth/Qwen-…
Guide: unsloth.ai/docs/models/qwen-…
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…
AlexAImaginator retweeted
Local Laya moggs Jev at @grok 4.7-built Tetris 🧩
An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air!
Run AI models locally -> atomic.chat
介绍比Jev快50倍，在你设备上跑的laya-mlx!
只在你的设备上占用最高1G内存
Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统
我将其移植到MLX,并且做了一些性能优化!
视频中就是这个模型在我的本地M3Max上玩贪吃蛇
这个模型能够以每秒决策60次的速度玩贪吃蛇！
github.com/mizorewww/laya-ml…
AlexAImaginator retweeted
Introducing Xiaomi MiMo-V2.6 — Pro & Flash.
Frontier intelligence, all the modalities, built in public.
🔹 Two omnimodal models, advancing through scaled reinforcement learning
🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks
🔹 Pro scores 46 on the Artificial Analysis Intelligence Index — the highest among open-source models
🔹 Stronger coding, computer use, 3D reasoning and creative capabilities
🔹 Open model weights, technical report, RL environments and training code
Blog：mimo.xiaomi.com/mimo-v2-6
AlexAImaginator retweeted
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.
AlexAImaginator retweeted
Here're some of the great stuff people are currently building ✨ You're welcome to add more in the comments.
@SamJWasserman
10 apps/tools to help with AI native filmmaking
github.com/wassermanproducti…
@sfxnz
An open sourced tool that allows anyone to serve and run evals for local models.
github.com/sfxnz/L.A.I.L
@Hikari_07_jp
A tool to help intuitively understand parallel inference and aggregation
xitter.cf/Hikari_07_jp/status/20…
@spark_arena
DGX Spark Community OSS tools
spark-arena.com
@WescheNex1q
Sacred geometry studio for iPad
vesica.studio/
@TraffAlex
AI Prompt Studio
github.com/lextraff-sudo/ai-…
@FoxRick01
Collie - your personal AI. With a dog.
github.com/FoxRick/Collie
@_nexuslink
Chromium annotation plugin
github.com/nexuslinkproducti…
@_ARahim_
Fine-tune LLMs on your Mac
github.com/ARahim3/mlx-tune
AlexAImaginator retweeted
We’re launching DeepSeek-V4-Pro today! 🚀
🔷 Major Agent upgrades with strong production gains!
🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, max for complex tasks.
🔷 Native OpenAI Responses API support, optimized for Codex with one-click setup.
V4 Pro is now available on app/web. Try it via “Expert Mode”.
V4 Pro is also available via API. Model names remain unchanged—please refer to the API docs for setup details.
