@nihui: zimage-ncnn can now do more than text-to-image! LanPaint inpainting and ControlNet control are here! No Python, no PyTorch, no diffusers, no CUDA needed. Only depends on C++ and ncnn, fully local offline V…

X AI KOLs Timeline Tools

Summary

The zimage-ncnn tool adds LanPaint inpainting and ControlNet control features. No Python/PyTorch/CUDA required, only depends on C++ and ncnn, supports fully local offline operation on Vulkan or CPU.

zimage-ncnn can now do more than text-to-image! LanPaint inpainting and ControlNet control are here! No Python, PyTorch, diffusers, or CUDA needed. Only depends on C++ and ncnn, runs fully local offline on Vulkan, also on CPU. https://zhuanlan.zhihu.com/p/2053882719927530196… https://github.com/nihui/zimage-ncnn-vulkan…
Original Article

Similar Articles

@MaxForAI: http://Z.ai and this ZCube paper from Tsinghua—worth a read for anyone in Infra. Many people's first reaction when talking about AI infra is still GPU, memory, quantization, and inference frameworks. But once you get into long context and Prefill-Decode separation, the network is no longer just a 'supporting role' in the data center. Every...

X AI KOLs Timeline

ZCube is a new network architecture that flattens the topology and mixes single/multi-rail access to optimize KV Cache transmission in long-context and PD separation scenarios. In the GLM-5.1 production cluster, it achieved a 33% reduction in switch/optical module costs, a 15% increase in GPU inference throughput, and a 40.6% decrease in TTFT P99.

@XAMTO_AI: ControlNet author Min Shen has come up with something new! The newly open-sourced FramePack directly lowers the barrier for video generation — runs on just 6GB VRAM, generates a 1-minute 30fps video with a 13B model, and on an RTX 4090 it takes only 1.5 seconds per frame. Such configuration requirements were unimaginable before. The core idea is frame-by-frame…

X AI KOLs Timeline

ControlNet author Min Shen has open-sourced the FramePack video generation model, which requires only 6GB of VRAM to run a 13B model, generates a 1-minute 30fps video, takes 1.5 seconds per frame on an RTX 4090, and comes with a one-click Windows package.

@op7418: https://x.com/op7418/status/2074728162018152817

X AI KOLs Timeline

The user released an open-source AI illustration skill called guizang-material-illustration, based on GPT-Image 2.0 and Codex Agent, which can generate 3D material explanation diagrams with Chinese labels, suitable for articles, weekly reports, PPTs, etc.