Updated
Updated
AILuma says more post-shoot changes to wardrobe, background, and lighting can now be made without bringing the crew back to set. The post gives no details on the tools, pricing, or availability of this capability.
AIMidjourney has published a video explaining how to use its new edit model for maintaining consistent characters and other edits. The post offers no further details on features, pricing, or availability.
AIMidjourney is testing fast models on alpha.midjourney.com and has added live previews in the Styles sidebar, showing how the latest prompt looks across liked and featured styles. Its edit model now changes only the selected pixels during inpainting and outpainting, allowing repeated edits without degrading image quality. Tiling with --tile also works better for V8.1/8.2, with seams between tiles now blending invisibly.
AIMidjourney is releasing a new version of --tile for seamless patterns in v8.1 and v8.2. It is also releasing an inpainting update that changes only the pixels users select, and previewing early real-time models on its alpha site.
AIModelScope released Qwen-Image-2.1-Fun-Controlnet-Union, a single checkpoint adding eight structural controls, including Canny, Depth, Pose, and Scribble, plus inpainting to Qwen-Image 2.1. Control and inpainting share one branch with 16 injection points across every second Transformer block, keeping the base model frozen and requiring no checkpoint switching. It runs at guidance scale 1.0 with CFG-distilled sampling and prefix KV caching, and is available under the Qwen Research License with base Qwen-Image 2.1 weights required.
AITencent Hunyuan's Hy Image 3.5 preview is now available on GMI Cloud at $0.024 per image. The pricing is reported as 8.8x cheaper than GPT Image 2 and 5.6x cheaper than Nano Banana Pro.
AIMeta AI announced Muse Realtime Avatar and directed readers to its research blog for details. The post itself provides no further technical specifications, features, or availability information.
AIAnt Ling's Ming-Image-0.1-Design, a text-to-image model built for graphic-design output and legible text rendering, is now available via Novita on OpenRouter. Novita launched it as a Day-0 partner with a free 14-day offer.
AIMicrosoft AI announced that its MAI-Image-2.6 image model can be tried on Microsoft Foundry and OpenRouter. The post provides links to both platforms but no further details on capabilities, pricing, or benchmarks.
AIMicrosoft AI reports its image model rose from 864 to 1147 Elo in nine months, a gain of 377 points per year. The company says that pace is 1.6 times the next-fastest climb on the leaderboard. The post does not name the model.
AIGoogle Gemini users can ask Gemini to generate multimedia, change backgrounds, and upscale image quality via Picsart. The post gives an example prompt: "Create a vibrant modern logo for an artisanal matcha café in Picsart."
AIGoogle Labs released six new Google Flow Tools built by creatives across architecture, sound design, and digital content, including Mondo Sónico, CaptionCast, ThumbnailForge, Surface, CollageMotion Pro, and SwissFlow Studio. Each tool targets a specific workflow, such as generating synchronized audio stems, transcribing and styling captions, or producing animated collages from text prompts. Users can try the tools, duplicate and remix them, or build their own by describing a task in Google Flow.
AIComfy Router is now live on the Comfy Developer Platform, giving developers one API to call frontier image, video, 3D, and audio models. Day one models include Seedance 2.5, MiniMax H3, Nano Banana Pro, GPT Image 2, Kling, and Black Forest Labs, and the provider for each job is selectable. Requests fail rather than silently switching providers, and inputs and outputs are deleted after 24 hours.
Why it matters: The post shows how one API key and a provider parameter let developers swap routes for media models without rewriting calls, with failed requests reporting the provider.
AIAlibaba's Qwen launched Qwen Intelligence with three mobile agents: a Mobile Planner Agent, a Mobile-Use Agent, and a Mobile Creative Agent. The post reports benchmark results including MobileWorld 82.1, MobileWorld-Real 92.2, and AndroidDaily 97.2, plus a 90% end-to-end success rate, and says the MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety benchmarks are open.
AITencent has released a preview of its Hy Image 3.5 image generation model, which product teams across Yuanbao, WorkRally, Ima, and other services are helping refine through co-design. Tencent Cloud prices the model at USD 0.024 per 2K output image, and it supports text-to-image and image-to-image generation with up to five reference images. Tencent said an internal blind evaluation found it on par with ByteDance's Seedream 5.0 Pro and slightly better than Nano-Banana Pro and Qwen-Image-3.0 Pro.
AITencent Hunyuan has made its Hy Image3.5 preview available on the OnSolo platform, free for two weeks. The model targets short drama character sheets, full-motion video game assets, and keyframes, with characters kept consistent across episodes and edits that refine rather than regenerate images. OnSolo's background post says the preview supports 5 references at 2K resolution and is free for Members during the two-week window.
AITencent Hunyuan's Hy Image3.5 preview is now available in ComfyUI, with a claimed 30% higher win rate in human evaluation than Hy Image3.0. The model handles text-to-image and image-to-image in one model at up to 2K resolution, with multilingual text and small print rendering correctly. It also keeps identity and product features consistent across scene, outfit, and style changes.
AIinclusionAI open-sources the Ming-Image-0.1-Design family, two complementary 6B models for visual-design workflows, under an MIT License. Design generates complete UIs, dashboards, infographics, and posters up to 2048×2048 with native transparent RGBA output, and Layer decomposes flattened graphics into independently editable RGBA layers.
AIAlibaba's Qwen-Image-2.1 is now the top open-source model in both the Image Edit Arena and Text-to-Image Arena, according to Arena. In the Image Edit Arena it scored 1367 points, placing #16 overall and just 3 points behind GPT-Image-1.5-high-fidelity at #15.
AIUnsloth Desktop received a hotfix update adding image editing for Qwen-Image-2.1. The update also fixes diffusers update issues, GGUF loading failures for Qwen-Image, and black artifacts during diffusion on A100 and consumer GPUs. Users should receive a banner prompting them to update.
AIUnsloth announced that Qwen-Image-2.1 FP8 and GGUF quantized versions should now run properly in Unsloth Desktop. The app supports both image generation and image editing with these quants. Further details are available on the Unsloth GitHub repository.
AIGoogle Flow now has more than 25 million people using it every month to create ideas, stories, and projects. Google is continuing to offer 50 additional daily credits to all users.
AIAlex Albert says Opus 5.5 has improved 3D modeling and vision for Blender work, letting users build an entire world from a single prompt. He shares a historically accurate render of San Francisco's Market Street in 1906, before the earthquake.
AIFelix Rieseberg of Anthropic shared an example of Opus 5.5 creating art after being asked only for "some subtle art." The post links to the generator as an artifact on claude.ai.
AIAnthropic's Felix Rieseberg says the new Opus 5.5 model writes more naturally than earlier models. He also highlights its strong generative computer art and drawing ability, noting it is not an image model yet produces attractive visuals.
AIDaniel Han says Qwen-Image-2.1 works in Unsloth Desktop through INT8, FP8, and GGUF builds, with Unsloth also releasing dynamic GGUFs for it. Pinned RAM offloading lets INT8 and FP8 fit under 6–8GB of VRAM while remaining relatively fast. The linked Unsloth post says the 7B model runs on 12GB VRAM and performs on par with Nano Banana 2.0.
AIUnsloth says the 7B Qwen-Image-2.1 text-to-image and editing model can run locally on 12GB VRAM using its GGUF builds. It also states that the model performs on par with Nano Banana 2.0, and that Dynamic FP8 can run on 6GB of VRAM via offloading for higher quality. The image lists int8 at 7.26 GB with mean LPIPS 0.064 and fp8 at 7.12 GB with mean LPIPS 0.112, and says int8 is the default.
Why it matters: The post gives concrete local-run settings, VRAM figures, and GGUF and FP8 options, which helps readers judge whether the model fits their hardware.
AITencent Hunyuan has released a preview of Hy Image3.5 on Miora, a design platform, and is offering it free for two weeks. The model keeps existing canvas workflows and remembers users' brand rules while making edits. Miora's background post says the free period runs through October 7 and supports up to 2K output for text-to-image and image-to-image.
AITencent Hunyuan posted a set of showcase images generated by its Hy Image3.5 preview model. The post presents the outputs as examples of the model's capabilities, without accompanying detail on methods or benchmarks.
AITencent Hunyuan replied that its model can edit images, not just generate them, answering a user's question. The post names no specific model, version, or benchmark.
AIQwen-Image-2.1 is now ready to run optimized on Intel hardware with Day-0 OpenVINO support, announced by Intel's developer account. The open-weight checkpoint handles both image generation and editing within a single model.
AITencent Hunyuan has launched a preview of Hy Image3.5, which it says wins 30% more often than Hy Image3.0 in human evaluation. The model supports text-to-image and image-to-image generation at up to 2K resolution with improved consistency, and is priced at $0.024 per image on the Tencent Cloud API, with reference images free. Two weeks of free access is offered through OnSolo and Miora.
AIXiaomi's MiMo-V2.6 combines code, design, and tool use to build frontend interfaces, presentations, Figma-linked visual assets, and videos. The post says MiMo-V2.5-TTS supports narration in video production, and that the model can compose music, including an orchestral piece for around ten instruments that can be converted to MIDI. On Design Arena, the Pro version reportedly performs comparably to Claude Opus 5 and GPT-5.6 Sol.
AIXiaomi's MiMo-V2.6 combines 3D spatial reasoning, multimodal perception, and computer use to turn text, images, or video into playable 3D worlds. The model coordinates agents to build scenes, write interaction logic, and refine results, and can create Blender objects for animation, 3D printing, and games. It also controls a Franka Panda arm in simulation via visual feedback and uses desktop tools to process data, inspecting results to adjust its next actions.
AIXiaomi's MiMo team released MiMo Gallery, a showcase where every 3D model, game, slide deck, video, music piece, and image was generated by MiMo-V2.6. The post previews MiMo-V2.6 as an upcoming model and points readers to the gallery for a first look.
AIModelScope now supports both inference and LoRA training for Qwen-Image-2.1 on its Civision platform. The post directs users to to start creating.
AISGLang-Diffusion now serves Qwen-Image-2.1 for text-to-image generation, multi-image editing, and transparent RGBA output. The quoted SGLang post reports 1024×1024 generation in 18.7s and editing in 21.7s on a single RTX 4090 24GB with CPU offload, using 22.7 GiB peak GPU memory, with no quantization.
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.
AIQwen-Image-2.1 is now supported in ComfyUI, and Qwen invites users to try it and share their creations. ComfyUI describes it as an open-weights 7B checkpoint that handles both generation and editing, with native 2K image generation and instruction editing from up to 10 reference images in one pass.