@Alibaba_Qwen Qwen-Image-2.1 editing test on NVIDIA DGX Spark
This is a AI post classified by Jev as AI image (a model release), kept by the AI Radar because it carries real work, not commentary.
@Alibaba_Qwen Qwen-Image-2.1 editing test on NVIDIA DGX Spark One 1600×672 city image → 4 funny near-lens LEGO Batman poses. 40 steps, bf16, original path (no KV cache/compile): 137.7–138.0s/edit ~137.9s average Peak VRAM: 36.97 GiB Prompt-only edits. No masks.
Posted by Ivan Fioravanti ᯅ (42.7k followers) 5 h ago · 17 likes · 1.1k views · view the original post on X. Kept by the AI Radar as AI image.
More AI work like this
- What can you actually do with AI in 1 minute, 1 hour and 10 hours? — @Stefan_3D_AI
- Gemini 4 Pro or flash in Arena (under the name gemini-3.7-flash) — @HarshithLucky3
- good morning everyone! — @nicdunz
- Qwen-Image-2.1 experiments on Apple Silicon (M5 Max, MLX, bf16) with my custom MFLUX — @ivanfioravanti
- Good morning my friends, may your hearts feel light and your minds feel clear today — @azed_ai
- All amazing new enemies I added to "It Wants You To Stay" today. This just keeps getting… — @AIandDesign
- Creeps that haunt the pool rooms of "It Wants You To Stay". Tons of new monsters today… — @AIandDesign
- xAI's Grok Imagine Image 2.0 takes #4 on the Artificial Analysis Text to Image… — @ArtificialAnlys
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. 27.1k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 17:35 UTC. Full method.