#Multimodal

AIQwen-Image-2.1 is now available as a live Hugging Face Spaces demo, letting users try image generation and editing in the browser without setup. The demo runs on a single checkpoint that handles both tasks. Background notes describe a 7B-parameter model supporting up to 10 image references, with integration into diffusers and ComfyUI.

AIPhilipp Schmid, who works on Google's Gemini, praised a series of demos, replications, and projects by Jev, which he says show what becomes possible with ultra-fast, multimodal models cheap enough for free use. He adds that the focus on coding agents makes it easy to overlook the broader range of tasks AI can handle.

AIDeveloper @mrgoodmantweets built MiniCPM-o Booking Desk, an open-source appointment booking agent that uses MiniCPM-o 4.5 for real-time, full-duplex voice and audio-visual interaction. The agent listens, speaks, and reads live booking status from an operator screen, while deterministic state control keeps execution reliable. An appointment is only booked after user confirmation.

AIQwen-Image-2.1 is presented as handling a variety of editing tasks while balancing performance across them. As one example, given a three-view character reference, the model generates a complete storyboard.

AIAlibaba's Qwen released Qwen-Image-2.1, which accepts up to 10 reference images. The post says it can produce high-quality results but gives no further details.

AIAlibaba's Qwen team released Qwen-Image-2.1 as an open-weights image model for both generation and editing, with a lightweight 7B architecture. The model natively generates and edits RGBA layers, supports up to 10 reference images for editing, and is available on GitHub, ModelScope, and Hugging Face.

AIAlibaba's ModelScope introduces Qwen-Image-2.1, a model that handles image generation and editing together, with native transparency and a compact 7B visual generation component. It adds KV cache reuse to speed up generation and editing while reducing memory use, especially with multiple reference images. The model can combine up to 10 reference images, make targeted local edits, and preserve portrait identity and product details.

AIQwen has open-sourced Qwen-Image-2.1, a unified text-to-image generation and image editing model with 7B visual generation parameters. The Hugging Face page for Qwen-Image-2.1-PE-I2I is a fine-tuned Qwen3.5-VL 9B prompt rewriter that turns vague editing instructions and input images into precise editing prompts, supporting up to 10 reference images.

Why it matters: The model card documents usage with transformers and diffusers, letting readers see how the editing prompt rewriter connects to the generation pipeline.

AIStepFun has released Step 5 Preview, a flagship model for agentic work that it says delivers frontier-level performance in software engineering and professional knowledge work, with particular strength in finance. The model is a 600B total, 27B active mixture-of-experts design with a 1M context window and vision support. StepFun says it offers substantially lower task cost at comparable intelligence, and open weights are scheduled for October 15.

AIGoogle AI Developers demonstrates Gemini 3.8 Live Extended Thinking as a workshop assistant that analyzes a user's workspace, reasons aloud, and guides a beginner through building a cyberdeck. The demo targets users with no prior experience building one.

AIEthan Mollick says GPT-6 Astra and Fable 5.1 already enable transformative impact and can reliably handle weeks of human work when properly guided. He cites GPT-6 Astra turning the 1977 text adventure Zork into a 3D action-adventure game and Fable 5.1 reconstructing Umberto Eco's Milan library in 3D from videos, photos, and catalogues.

AIMustafa Suleyman, owner of the source account associated with Microsoft and Copilot, says the post claims the best image generation quality-price performance in the world. The post itself gives no specific model, price, or benchmark figures. Background from Artificial Analysis says Muse Image, MAI-Image-2.6, and GPT Images 2.5 recently shifted text-to-image price and speed frontiers.

AIHailuo AI's post suggests that a single 3x3 storyboard image can be converted into a video using the MiniMax H3 Max r2v model at 480p for 15 seconds. The quoted post describes settings with Quality prompt tuning and standard reference strength, and asks for a 2D animation with panel-to-panel cuts while excluding multiple panels and BGM.

AILiquid AI released LFM2.5-VL-3B-DSpark, a speculative-decoding draft model for its LFM2.5-VL-3B vision-language model. The source reports decoding up to 2.66× faster on a single H100 with SGLang, up to 3.13× on Apple M5 Max with MLX-VLM, and up to 2.14× on Apple M3 Ultra with llama.cpp, with output unchanged under greedy decoding.

AIVC-Attention, developed by Nunchux AI and collaborators, accelerates attention for MiniMax-H3 without retraining. In the B200 evaluation, it shows better fidelity than SageAttention2, with V-Smooth reducing value quantization error and ExpCast-FP8 speeding up softmax.

AIAlibaba Wan's post advises beginners making AI video to design a viewing experience and tell an emotion-triggering story rather than chasing the prettiest frame. It notes a single 30-second shot can be enough, citing the filmmaker behind Soulscape and Johnny Mai from Alibaba Cloud. The post promotes bringing Wan3.0 to teams via a sign-up form.

AIvLLM now supports NVIDIA hardware video decoding through PyNvVideoCodec, moving video decoding off the CPU so multi-GPU video captioning can scale to 8 GPUs. In benchmarks on 8xH100 GPUs, GPU-based decoding provides more than double the throughput of the CPU-based decoder for Qwen/Qwen3-VL-8B-Instruct with 8 single-GPU vLLM replicas. The functionality is included in standard CUDA vLLM releases, and PyNvVideoCodec==2.0.4 is required for custom installations.

AIMike Krieger, Anthropic's account owner, used an interactive Claude artifact to visualize the Iron Tangle level from Dungeon Crawler Carl, saying it helped him finally understand the layout. The post shares a link to the artifact, with no further details about its features.

AISenseTime released its SenseNova U1.5 technical report, describing an open-source 8B native MoT unified model that connects understanding and generation through shared attention. The model reports 68.2% on VBVR-Pro-Bench, ahead of Nano-Banana-Pro (56.4%) and GPT-Image-2 (50.7%), and its full training recipes, including SFT, RL, and multi-expert on-policy distillation, are open-sourced.

AISenseTime chief scientist Lin Dahua argues that native multimodal AI, which processes language, vision and other information in one shared model, is essential for AI to move beyond coding into industries and the physical world. SenseTime released the open-source SenseNova U1 in April and U1.5 Lite nearly four months later, and reported first-half 2026 revenue of RMB 2.91 billion, up 23.4% year-on-year. Lin's claim that a breakthrough could come within two years is the source's prediction, not a confirmed result.

AIOpenBMB says Dubedo is the kind of product it hoped VoxCPM2 would enable, citing speaker-aware cloning, multilingual generation, and an editing studio. The post praises @dubedostudio's work, while the background post describes Dubedo as dubbing into 30 languages with per-speaker voice cloning and a beta open for trial.

AIMosaic, Ponder Studio, and Revyl tested Google's agentic video understanding with early-access Gemini Flash models for production video editing, B-roll selection, and mobile app testing. Mosaic reported a 97% cut in median token usage for its video agent Motion, and Ponder Studio reported a 0.967 F1 score with roughly 72% lower token costs when selecting B-roll. Revyl reported a 65% accuracy improvement in catching UI bugs and animation stutters, and the capability is available now via the Gemini API for video uploads and YouTube videos.

AIAnthropic is merging Claude Cowork and chat into one Claude, and Claude Design is integrated so users can ask for slides, designs, or docs without switching apps. Claude decides from the prompt whether to give a quick answer or do deeper agentic work, and users can still stop, redirect, or adjust its effort. The change rolls out to Pro and Max over the next few weeks.

AIPeking University's Yu Zhaofei team and the Beijing Academy of Artificial Intelligence (BAAI) released Brainμ-Spike, a small convolutional network for spike camera image reconstruction that is paired with the Brainμ model. The package includes weights, inference scripts, and evaluation tools, but the base large model and LoRA weights are not yet released, so the full generation pipeline cannot run from this repository alone.

AIinclusionAI has published Realtime-Venus on Hugging Face with two 9B checkpoints: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for audio-only conversation. Both are built on MiniCPM-o 4.5 with a Qwen3-8B backbone and support full-duplex dialogue, proactive responses, and training-free long-video memory. The asynchronous Realtime-Venus-Harness runtime is hosted in a separate GitHub repository.

AITencent's WeVisDoc-4B, fine-tuned from Qwen3-VL-4B-Instruct, scores 95.38 Overall on OmniDocBench v1.6 and 75.54 mean Overall across three PureDocBench tracks. The end-to-end parser converts page images into structured Markdown with LaTeX formulas and HTML tables, and the 2B variant is also available. The repository provides vLLM serving scripts with a 32768-token default context and a Python client for batch processing.

AIHiDream.ai launched vivago R1, a content creation agent, globally, with a domestic version upgrade. The company says R1 can output five-minute high-quality videos through agent planning, with a claimed 85% usable-output rate and support for multi-round extensions. It also released HiDream-O1-Video-1.0, a native omni-modal video model supporting single shots of 5 to 20 seconds at 1080p.

AIGoogle AI Studio released Gemini 3.8 Live, a native speech-to-speech model with an Extended Thinking variant, and made it available through the Live API. Gemini 3.5 Transcribe, released last month, supports 85+ languages with a reported 4.0% streaming and 2.6% non-streaming Word Error Rate, and accepts a custom vocabulary of up to 1,000 terms. Live API audio pricing is listed at $0.005/min for input and $0.018/min for output.

Why it matters: The post lists concrete Live API capabilities, per-minute audio pricing, and transcription accuracy figures, helping developers weigh voice agent options against their own cascaded pipelines.

AIGoogle's Gemini Notebook now offers live spoken Q&A over class materials in about 100 languages, and lets students record lectures on the go with audio notes saved automatically to a chosen notebook. University students in 140+ countries can also still get a free Google AI Plan for higher limits and access to more Google products.

AIGoogle introduced two live dialogue models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, available through AI Studio and the Gemini API. Gemini 3.8 Live is built for scale and cost efficiency, combining conversational intelligence with fluid dialogue and visual grounding. The Extended Thinking variant targets high-complexity tasks with increased intelligence and multi-step reasoning.

AIGoogle AI announces Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking as its most advanced Gemini Audio models. Gemini 3.8 Live is built for scale, speed, and cost efficiency, handling mid-sentence interruptions, transitions across 97 languages, and visual context through Search Live. Gemini 3.8 Live Extended Thinking reasons and speaks in parallel, narrating its progress on multi-step tasks such as event planning.

AIGoogle DeepMind introduced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, two live dialogue models for voice agents. Extended Thinking scores 82.6 on Artificial Analysis' Speech to Speech Quality Index, 68.6% on τ-Voice, and 97.7% on Big Bench Audio. Gemini 3.8 Live is rolling out now in the Gemini API, Google AI Studio, and Search Live, with enterprise access in private preview.

Why it matters: The release covers a voice model's benchmark results and availability across developer, enterprise, and consumer products, useful for judging voice agent options.

AINVIDIA's RT-DETR Hand Detection v1.0 detects and localizes left and right hands in RGB images, outputting 2D bounding boxes with per-hand confidence scores in a single pass. The model, built on RT-DETRv2-S with HGNetv2-S backbone and about 20M parameters, is intended as a region-of-interest stage for downstream 3D hand pose estimation and is exported to ONNX. The source describes it as for demonstration purposes rather than production use, runs on NVIDIA Lovelace GPUs under Linux, and is licensed under the NVIDIA Software and Model Evaluation License.

AIOdyssey says its new Odyssey-3 model could enable physical agents, a new kind of agent that interfaces natively with physical and virtual systems. The company expressed excitement about the promise its models are showing, linking to an introduction page for Odyssey-3.

AIOdyssey announced Odyssey-3, a foundation world model it describes as a major step forward. The post claims it can control robots, power humanoids, drive cars, train AIs, pilot drones, and play video games, though it gives no benchmarks or technical specifications.

AIGoogle reports that its technologies and products now power everyday interactions in more than 300 languages used by over 7 billion people, about 86% of the global population. The post describes new speech models, including Gemini 3.5 Live Translate and Gemini 3.5 Transcribe, plus the TranslateGemma open translation models trained across 55 languages.

AIIn a Paint recreation test, GPT-5.6 Astra built the image from layered geometric shapes, while Qwen3.8 Max worked pixel by pixel. Qwen's output looks closer to the original, but Raschka argues this single example does not show either model generalizes better or has stronger computer-use or visual understanding, and it illustrates how benchmarks comparing only final results can be misleading.

AIMiniMax Design lets a single brief drive a full production workflow on one canvas, with the Astra agent working in Blender through an official connector to build the scene and camera direction. The final video is generated with MiniMax H3 from the same canvas, with outputs syncing directly onto the canvas.

AINVIDIA Research released FoundationStereo-small, a zero-shot stereo depth model that takes an RGB stereo pair and outputs a disparity map, on Hugging Face. The model has about 6.3×10^7 parameters and ships as ONNX files at fixed 576x960 and 320x736 resolutions, with TensorRT and ONNX runtime support. It is licensed under the NVIDIA Open Model License and is ready for commercial use.

AIGoogle DeepMind released EmbeddingGemma 2, an open model under Apache 2.0 that maps text, images, video, and audio into one shared 768-dimensional vector space. The model has 740M total parameters and supports 8,192-token context, with Matryoshka truncation to 128d, 256d, and 512d. The source reports 14% better code-task performance than EmbeddingGemma 1 and says it is designed for consumer hardware such as phones and laptops.

Why it matters: The release combines text, image, video, and audio retrieval in one 768-dimensional space at 740M parameters, a useful reference for on-device multimodal search design.