@HuggingPapers: AMD just shared an NPU-optimized Stable Diffusion 3.5 Medium on Hugging Face Built to run text-to-image generation effi…
Summary
AMD 发布了针对其 Ryzen AI NPU 优化的 Stable Diffusion 3.5 Medium，可在 Hugging Face 上获取，实现高效的本地文本到图像生成。
View Cached Full Text
Cached at: 10/30/26, 07:14 AM
AMD just shared an NPU-optimized Stable Diffusion 3.5 Medium on Hugging Face
Built to run text-to-image generation efficiently on AMD Ryzen AI NPUs https://t.co/NRlhOhNjiv
Similar Articles
@HuggingPapers: NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-…
NVIDIA released AnyFlow, the first any-step video diffusion model for text-to-video generation, allowing smooth quality scaling across inference budgets (4 to 50 steps).
@HuggingPapers: Microsoft just released Lens on Hugging Face A 3.8B parameter text-to-image model delivering efficient training and hig…
Microsoft released Lens, a 3.8B parameter text-to-image model on Hugging Face, capable of efficient training and high-resolution generation up to 1440×1440.
@HuggingPapers: NVIDIA just released an NVFP4-quantized DiffusionGemma on Hugging Face A 26B MoE multimodal model generating text via p…
NVIDIA released a 26B MoE multimodal model called DiffusionGemma on Hugging Face, using NVFP4 quantization and achieving over 1,100 tokens per second on Hopper hardware.
@petruspennanen: TensorFold 1.0.5 is out with its first AMD code! It has a runtime for AMD GPUs (tested on gfx1150 / gfx1151 / gfx1201) …
TensorFold 1.0.5 发布首个 AMD GPU 运行时（支持 gfx1150/gfx1151/gfx1201），在 Strix Halo 上跑 Qwen3.6-35B-A3B 解码速度比 llama.cpp 快 36-54%，预填充快 40%，目标是让单一模型跨 NVIDIA、Mac 和 AMD 运行且远快于 llama.cpp。
AMD contributes ONNX Runtime backend to FFmpeg DNN filter
An AMD engineer contributed an ONNX Runtime backend to FFmpeg's DNN filter, enabling AI model inference on GPU and NPU platforms for tasks like upscaling and object detection, notably making Ryzen AI NPU useful for FFmpeg.