Skip to content
Date and source

Dates follow the news timeline in Beijing time and include both endpoints.

Oct 13Tue
  1. ComfyUI Wiki · 工作流与开源创作分享78

    Fish Audio releases Drama 3 speech synthesis model, supporting 16 characters and natural-language performance instructions

    Fish Audio released its next-generation speech synthesis model Drama 3 on October 13, 2026, an open-weight 35B MoE model activating 3B per token.

    Why it matters: The 35B open-source speech model supports same-track generation of 16 characters and natural-language performance instructions; its pronunciation robustness data can be used to assess dubbing and audiobook workflows.

  2. あいきみ · 图像编辑与LoRA实测36

    Iris3B Illustration and the Style-Adjusted IrisKimi-3B-v1 Released, Based on Full-Parameter Fine-Tuning on Google Colab

    Based on Speridlabs' Iris-3B, the author completed full-parameter fine-tuning of the roughly 3-billion-parameter model itself on an A100 80GB on Google Colab, and released the illustration model Iris3B Illustration plus IrisKimi-3B-v1, which adds 600 updates on top of it to adjust the art style.

Oct 12Mon
  1. 腾讯 ARC · 创作模型60

    Tencent ARC Open-Sources Multi-Person Video Generation Model Multics

    Tencent ARC released Multics on Hugging Face, achieving scalable multi-person video generation through layered communication. The repository includes the complete 4-player Multics DiT checkpoint, configuration, Wan2.2 VAE, UMT5 text encoder, and tokenizer; the same checkpoint supports 6-, 8-, and 10-person generation without retraining. The weights are distributed under the Apache 2.0 license.

    Why it matters: Tencent ARC open-sources the multi-person video generation model Multics, where the same weights can scale to 10 people, letting creators evaluate generation options for multi-person scenes.

Oct 11Sun
Oct 10Sat
  1. 开源中国62

    Nano Banana 2.1 in-depth hands-on: 4K direct output and Chinese typography improve, but consecutive image edits still have pitfalls

    Google updated its image-generation model Nano Banana to 2.1 on October 6, switching the base to Gemini 3.6 Flash, with upgrades focused on four areas: visual design, mask editing, subject consistency, and image realism. Hands-on testing shows the image quality supports 4K direct output from the original image with solid macro detail, and the clarity and typography of Chinese text have also improved noticeably, but the consecutive image-editing step still has pitfalls to watch for.

  2. 可灵官方博客58

    Creator hands-on test of Kling 4.0: character consistency, multi-image transitions, and style switching performance

    Korean visual creator 서오키 (@oasis.seo.ai) was invited by Kling to hands-on test Kling 4.0, using three creative experiments to examine Omni Reference, style transitions, and character consistency. She said Kling 4.0 can coherently handle subtle movements such as eye contact, expressions, and gestures, preserves the original image's color tone and texture when connecting multiple images, and keeps character form and movement stable during repeated switching between live action and animation, reducing repeated generation and post-production fixes. She also hopes Sound Effects, character consistency, and fine control will continue to improve.

Oct 9Fri
  1. SuSu_酥酥66

    Alibaba Tongyi open-sources Qwen-Image-2.1-Turbo, producing 2K images in 8 steps

    Alibaba's Tongyi open-sources Qwen-Image-2.1-Turbo, an accelerated checkpoint based on Qwen-Image-2.1 that uses the same 7B visual generation architecture; text-to-image and natural-language editing require only 8 denoising steps, and the official release says it can still generate 2K images and supports continuous editing such as adding accessories and changing scenes.

    Why it matters: Qwen-Image-2.1-Turbo achieves 2K text-to-image and natural-language editing with 8 denoising steps, and offers two onboarding paths: Diffusers and API.

  2. 通义千问 · 图像与音频模型62

    Alibaba releases Qwen-Image-2.1-Turbo accelerated image generation model

    Qwen released Qwen-Image-2.1-Turbo, an accelerated checkpoint of Qwen-Image-2.1 for text-to-image and image editing, requiring only 8 denoising steps.

    Why it matters: 8-step sampling and KV cache reuse of text and reference image context let creators assess the speedup potential of their image generation and editing workflows.

  3. Midjourney 官方更新50

    Midjourney tests Thinking Mode for image generation

    Midjourney is testing a new Thinking Mode for image generation on the Alpha website (alpha.midjourney.com), which users can run by clicking "Rerun (Thinking)" in the lower right corner of a job's lightbox. Tests show the mode helps improve prompt accuracy, text layout, and image coherence. Midjourney says it may in the future make it a general thinking mode, or "add more thinking" after a job is completed.

Oct 8Thu
  1. 机器之心 · 公开公众号 RSS73

    Shengshu Technology Releases Vidu Q4 Preview, Starting at 0.09 Yuan/Second

    Shengshu Technology has launched Vidu Q4 Preview, the first preview version of Vidu Q4 for creators, focusing on enhancing character performance, camera language, and complex visual effects. The launch price starts at 0.09 yuan per second, allowing up to 5 times more content to be generated with the same budget.

    Why it matters: Vidu Q4 Preview combines a launch price of 0.09 yuan per second with 15 reference images and 2K/4K output, providing a basis for judging the cost range of AI video mass production.

Oct 7Wed
  1. GitHub:AI视频开源项目发现40

    Self Gradient Forcing Plus: Decoupled gradient flow enables autoregressive video generation

    Teams from Tsinghua University and JD.com's Joy Future Academy have open-sourced Self Gradient Forcing Plus (SGF+), which resolves gradient conflicts in SGF by separating context writing and denoising parameters, enabling autoregressive video generation of up to 24 hours using only a 5-second training window.

  2. SuSu_酥酥22

    Opus 5.5 renders a Pixar-style Dots short film in code

    Opus 5.5 used pure code to generate a Pixar-style short film for its rival Dots, with felt-like fuzzy characters, big-eyed highlights, and shallow depth of field, rendered frame by frame in real time entirely in the browser, without opening modeling software or using any assets. Six fuzzy Dots surround a ball of white thread woven into a white flower knot, and the ending states the theme: "Six colors added together make white light." The lighting, fur, reflections, and depth of field effects are close to studio live-action footage.

  3. 可灵 Kling22

    Kling 4.0 to appear at ACFM in Busan

    Kling announced that Kling 4.0 is about to be released and will showcase a series of real projects created with the model at ACFM in Busan, South Korea, from October 10-13. Kling said its focus is no longer just on what AI can generate, but on whether it can understand a director's creative intent, maintain character and narrative coherence, and integrate into professional production workflows for animation, live-action film and television, and series. It will discuss with filmmakers, studios, and content platforms how generative AI is moving from creative experimentation to professional production.

  4. Oimi · 中文图像视频教程67

    Google releases Nano Banana 2.1: half the price, panoramic aspect ratios, and 14-image fusion

    Google officially released the image generation and editing model Nano Banana 2.1 (model ID: gemini-nano-banana-2.1) in the Gemini API, at about $0.034 per 1K image, roughly half that of Nano Banana 2.

    Why it matters: Google's image model 2.1 cuts the per-image cost by about half and adds panoramic aspect ratios and 14-image fusion, which can be used to evaluate whether to migrate an existing image-generation pipeline.

  5. SuSu_酥酥78

    Google Releases Nano Banana 2.1 Image Generation and Editing Model

    Google has officially released the Nano Banana 2.1 image generation and editing model, which the company says comprehensively surpasses the previous generation in visual design, precise mask editing, and subject consistency, with more natural and realistic images. This version has rolled out across Gemini, Search AI Mode, AI Studio, Flow, Stitch, Google Ads, and enterprise platforms.

    Why it matters: Google's image generation model gets an upgrade, calling out changes in three capabilities—visual design, mask editing, and subject consistency—and has rolled out across multiple product lines.

Oct 6Tue
  1. FastVideo 视频模型 · 模型发布62

    FastVideo Releases FastH3 Trim Lightweight Model and ComfyUI Repackaged Files

    FastVideo released the experimental lightweight model FastH3 Trim, reducing transformer blocks from 50 to 42, using rank-16 timestep conditioning, 8-step sampling, with a 4.2x smaller size than the base H3 and faster than FastH3 V2.

    Why it matters: FastH3 Trim offers a lighter video generation solution with 42 layers, 8-step sampling, and 4.2x size compression, along with ComfyUI files and parameters for various precisions.

  2. Theoretically Media blog62

    Two Open-Source Video Models Released: Prism and Kandinsky 6.0; Nano Banana 2.1 Goes Live

    Tencent's Hunyuan team, in collaboration with Fudan University, released the open-source video model Prism, which natively generates 2K video with audio—approximately 10 seconds at 24fps with 48 kHz audio. It only supports image-to-video, requires an 80 GB GPU for 720p, and has no quantized version yet. The code is under the Tencent-Hunyuan GitHub organization, preview weights are on a personal Hugging Face account, and Tencent has not issued an official announcement.

Oct 5Mon
  1. GitHub:AI视频开源项目发现82

    Kandinsky 6.0 open-sourced: synchronized audio-video generation models, in Lite and Pro tiers

    kandinskylab released the Kandinsky 6.0 Video series of diffusion models, including a 3B-parameter Lite and a 29B-parameter Pro, capable of generating 5-second videos with 44 kHz synchronized audio (including lip-sync), supporting text-to-audio-video and image-to-audio-video, and paired with a super-resolution model that upscales output to Full HD (1920×1080).

    Why it matters: Kandinsky 6.0 has open-sourced video generation models with synchronized audio and lip-sync, and provides measured runtimes for various GPU tiers, making it easy for creators to assess local deployment costs.

Oct 4Sun
  1. 可灵 Kling60

    Kling breaks down Kling 4.0 short film "The Beat": 30-second continuous shot and Omni Reference

    Kling released a behind-the-scenes article breaking down shot by shot the Kling 4.0 features used in its short film "The Beat," which has over 5 million exposures on social platforms. The article mentions that Kling 4.0 natively supports 30-second continuous generation, Omni Reference supports up to 15 multimodal references per task, Multi-Keyframe supports up to 10 keyframes, and it has 10-bit HDR output, upgraded stereo audio, and improved lip sync.

Oct 3Sat
  1. FastVideo 视频模型 · 模型发布62

    FastVideo releases the FastH3 Trim 8-step audio-video generation model

    FastVideo released the experimental model FastH3 Trim, which removes 8 of the least impactful blocks from FastH3 V2's 50 MiniMax H3 transformer blocks and replaces each block's AdaLN timestep projection with a shared rank-16 basis, trained with 8-step DMD2 (checkpoint 300), enabling 8-step text-to-video generation with synchronized audio.

    Why it matters: FastH3 Trim uses pruning plus shared AdaLN to bring 8-step audio-video generation to consumer-grade hardware, and can be compared against V2 to weigh image quality against size.

  2. IndexTTS · 语音模型60

    IndexTeam Releases Index-Translate-35B-A3B-preview Multilingual Translation Model

    IndexTeam has released Index-Translate-35B-A3B-preview, a multilingual text translation model based on Qwen3.5 with 35B total parameters and 3B active parameters in an MoE architecture. It supports 150 languages and natively supports end-to-end image translation without requiring external OCR.

    Why it matters: The Index-Translate family adds a 35B-A3B preview version supporting 150 languages and direct image translation, allowing evaluation of its low-resource language performance against report data.

Oct 2Fri
  1. 可灵 Kling72

    Kling 4.0 enters closed beta, official release in October

    Kling 4.0 has entered closed beta, with the official release scheduled for October this year. The new version upgrades audio and visuals, supporting stable dynamic motion, high-quality stereo, more precise lip-syncing, up to 4K resolution and 10-bit HDR output, and can generate videos up to 30 seconds long.

    Why it matters: Kling 4.0 has entered beta testing, allowing creators to understand its changes in dynamic stability, long-take capability, and consistency.

  2. 可灵官方博客62

    Kling 4.0 enters closed beta: creators test 30-second long takes and multi-shot consistency

    Kling 4.0 has entered closed beta, with an official release planned for October this year; upgrades include stable dynamic motion, high-quality stereo audio, more accurate lip sync, up to 4K resolution and 10-bit HDR output.

    Why it matters: Kling 4.0 enters closed beta; creators test 30-second long takes, motion stability and multi-shot consistency, which can help judge whether a commercial production pipeline is worth switching to.

Oct 1Thu
  1. Runway38

    Runway launches Project Continuum real-time video interface system

    Introducing Project Continuum from @runwayml_labs, a new operating system research app built around real-time video interfaces. Today we share early previews of four new ways to interact with computers: Portals, Visual Thinking, Responsive Video Interfaces, and Interactive Worlds. Interface World Models like Solaris are reimagining what an interface can be.