Intel AI Playground version 2.6.0 has arrived with numerous practical updates that make experimenting with local generative models easier and more predictive. The release introduces new models, including GPT-OSS 20B, Wan 2.1 VACE, and Flux.1 Kontext into the Playground, and it updates core frameworks including OpenVINO, ComfyUI, and Llama.cpp. A new backend version control setting lets users choose which framework releases to install and run, so you can stay current between Playground updates. The standout workflow is Edit By Prompt, powered by Flux Kontext, which lets you change or combine images using plain language without manual masking. That means you can remove a microphone, turn a photo into anime, or merge two shots into a single cyberpunk scene just by describing the edit you want.

The update also expands video capabilities for systems with Intel Arc discrete GPUs, adding Image-to-Video and Video-to-Video workflows using Wan 2.1 VACE. The notes suggest starting at 512x512 pixels and about 49 frames to manage VRAM and iteration time, and they warn that a four-step LoRA setting can reduce compute at the cost of motion freedom. Convenience improvements include drag-and-drop thumbnails, a direct ComfyUI launch for node-level tweaks, Create and Enhance powered by PyTorch 2.8, Quick Access modes for Standard and HD, and a cleaner workflow menu. Image folders now use YYYYmmdd naming for easier sorting. Llama.cpp exposes an adjustable context size and a Vulkan backend for improved performance. Users can try more AI capabilities locally, and run their entire workflows from the central software.