Yesterday you could already make realistic images locally with Krea 2 on an RTX card.
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Yesterday you could already make realistic images locally with Krea 2 on an RTX card. Today, with Qwen-Image 2.1, you have Nano Banana Pro capabilities on your own hardware. Text rendering, character consistency, multi-reference composition, native alpha, native 2K on your desk. Here is my first run. It will run on a RTX 3090/4090/5090 WHAT I RAN Qwen-Image 2.1, INT8 build, on my RTX 4090 through ComfyUI. 7B model, full weights download 17.3GB. Peak VRAM across all my runs was 16.2GB. Any 24GB card handles it, and the same build is validated on the 3090. No API. No subscription. No rate
Posted by Yume_X (2.1k followers) 1 h ago · 0 likes · 209 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- llama.cppで起動したMiMo-V2.6-Distill-Qwen-9Bにやらせた。ラーメン屋ベンチの結果です。動画をご査収ください。 — @studio_yebisu
- the open frontier intelligence list keeps on growing. — @arjunkocher
- Qwen Image 2.1 Is OPEN WEIGHTS… Nano Banana 2 at HOME ! https://youtu.be/6teCD4Kq4wA — @Tech2Wild
- 60.4 Qwen 3.8 Flash Next 1 spark — @TechMDAI
- New AI model alert! Xing4.0-29B-A4B-GGUF just dropped. It's a conversational… — @HuggingModels
- Xiaomi, in the spirit of R1 moment, releases a small Qwen distill. 3.5 9B is a strong… — @teortaxesTex
- Uncensored Xiaomi MiMo-V2.5 model you can run locally. — @0x0SojalSec
- One again for those in the back: — @teortaxesTex
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 40.6k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 00:02 UTC. Full method.