#Event# | 🎨🌸 Nearly 90-year-old artist Chen Jialing has spent decades exploring that question, blending the traditions of Chinese ink painting with fresh forms across paper, porcelain and silk. His works—from lotus flowers and landscapes to colorful porcelain and Chinese silk tapestry—will be featured in “The Present Beyond Time: Chen Jialing Art Exhibition” at the Guangdong Museum of Art (Bai’etan). ✨ Click to learn more details: #Guangzhou# #GuangdongMuseumofArt# #ChenJialing# #ChineseArt# #InkPainting# #ChinesePainting# #ArtExhibition# #ChineseCulture#

Eight controls and inpainting in one checkpoint. Qwen-Image-2.1-Fun-Controlnet-Union adds precise structural guidance to Qwen-Image 2.1. 🎨 🤖 🎛️ One control branch supports Canny, Depth, Grayscale, HED, Lineart, MLSD, Pose, and Scribble with no checkpoint switching. 🖌️ Control and inpainting share the same branch, allowing masked regions to follow both the prompt and a structural reference. 🧠 Sixteen injection points guide every second Transformer block while keeping the base model frozen. ⚡ CFG-distilled sampling runs at guidance scale 1.0, while prefix KV caching accelerates repeated denoising steps. 📜 Qwen Research License. Qwen-Image 2.1 base weights are required.

one wrong word shouldn't mean redoing a whole voiceover. @FishAudio's Drama 3 lets you fix a single word with audio inpainting. the rest of the take stays untouched. their most emotive voice model yet. 83 languages, and you direct it in plain language. #ad#

Can you figure out which one is the original and which one was done with MiniMax H3 using masked inpainting? Testing it on the infamous Justice League scene where Henry Cavill’s mustache was digitally removed. 👀

A few quick updates today! We're releasing a new version of --tile for seamless patterns in v8.1 and v8.2. We're releasing a new version of inpainting that only changes pixels you select and we're previewing an early look at real-time models on our alpha site. Enjoy!

We’re gonna start testing our first V8.2 edit model today. This model supports editing with instructions, generating images with other images (up to 4 references), brush-based inpainting, and outpainting. It also works with personalization, moodboards, and srefs. Have fun!