Skip to content
Date and source

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

Oct 4Sun
  1. CoAnimator · 可编辑视频与动画工作流34

    What Is the Agentic AI Video Tech Stack? Models, Agents, Tools, and Workflows

    Agentic AI video consists of replaceable layers including models, agents, skills, MCP/tools, projects, renderers, feedback loops, and workflows, with each layer's failure corresponding to different repair methods. Models handle reasoning but cannot operate on project files; agents (such as Claude Code and Codex) can read and write files, run commands, and view their own rendered results.

  2. ArchiGen AI · 图像生成与ComfyUI实战38

    ComfyUI Architectural Rendering Tutorial: Lock Lighting First, Then Fix Glass Reflections

    The correct order for fixing reflections in ComfyUI architectural rendering is to first lock the final lighting, then use a glass mask combined with depth or Canny guidance to repaint only the glass areas at low denoise. The official ControlNet examples note that the Apply node does not automatically generate depth or Canny maps—users must provide matching inputs themselves. The official inpaint workflow also only repaints the selected area. The author uses five checkpoints for quality control and finally confirms with a difference mask that changes have not exceeded the mask boundaries.

  3. Aitrepreneur · YouTube 创作视频62

    Aitrepreneur Releases a ComfyUI Multi-Image Editing Workflow for Qwen Image 2.1

    Aitrepreneur showcased a custom Qwen Image 2.1 ULTRA ComfyUI workflow supporting multi-image editing with up to 9 images, allowing users to replace characters, remove or move objects via text prompts. The workflow also includes operations such as inpainting, outpainting, and background removal, and is used in conjunction with additional tools and LoRAs.

  4. 小智博客 · 音视频实践38

    MoneyPrinterTurbo hands-on test: can AI video generation get local production, remote access, and license verification working?

    The hands-on test examines whether MoneyPrinterTurbo can truly run the entire pipeline of "topic → script → assets → voiceover → subtitles → finished video," covering three stages: local production, remote access, and license verification. The original article lays out a fairly complete test path; the focus is not the broad question of "whether AI can make videos automatically," but the practical usability of the tool's end-to-end workflow.

  5. 小智博客 · 音视频实践38

    Don't want to learn React first? Use Codex to help you finish your first Remotion motion-graphics video

    With Codex's assistance, you can complete your first Remotion motion-graphics video even without being familiar with React. Remotion writes video frames as React components, with animation, layout, and data all controlled by code, skipping the traditional workflow of cutting assets on a timeline, setting keyframes, adjusting transitions, and then waiting for rendering.

Oct 3Sat
  1. openscreen · 公开创作项目发布34

    OpenScreen 2.0 released: a polished demo on your first recording

    OpenScreen 2.0 is released, built around the idea that it "looks good without tweaking settings, and won't look bad even if you do," adding an editor and support for automatically planning zoom shots based on clicks. The new version halves the default cursor size, raises the 1080p60 export bitrate from 8 Mb/s in 1.x to 18.7 Mb/s, normalizes audio to -16 LUFS, and switches transcription to Silero VAD with re-alignment of each word's timing. This version remains completely free for personal and commercial use, with no paywall, and 1.x projects can be opened directly.

  2. note · ai_to_hibi_note · 图像视频创作分享36

    Writing 8 short stories with local AI on an ordinary laptop and turning them into narrated videos: a hands-on test of Qwen3.5, FLUX.2 klein, and VOICEVOX

    On an ordinary laptop without a GPU (Ryzen 7 7735HS, 32GB RAM), local AI was used to have Qwen3.5 (4B) write stories, FLUX.2 klein 4B draw illustrations, and VOICEVOX provide voiceover, producing a 40.9-second vertical narrated video with 6 scenes.

  3. openscreen · 公开创作项目发布10

    OpenScreen v2.0.0-rc.15 released

    OpenScreen released v2.0.0-rc.15; changes since v2.0.0-rc.14 include: the preview feature no longer decodes a substitute camera when a clip has no camera, and records the free-running decode budget; on the testing side, a passing record of the macOS computer-use end-to-end test was added, and it was verified that the substitute camera never moves.

  4. MoneyPrinterTurbo · 开源创作项目发布50

    MoneyPrinterTurbo v1.3.8 released: adds VoxCPM voice cloning and a local video project CLI

    MoneyPrinterTurbo v1.3.8 adds VoxCPM reference-audio voice cloning and tone/emotion transfer, and adds the MuAPI video asset source, Fluxion AI, iFlytek Spark (Astron MaaS), and several other LLM providers. Concurrency for asset and clip rendering is configurable, defaulting to 1 (serial) for both; it also launches a CLI-only local video project workflow that supports version tracking and reuse of unchanged rendered outputs.

  5. ArchiGen AI · 图像生成与ComfyUI实战22

    4K Is Not a Delivery Requirement for Architectural Rendering: Five Steps for ComfyUI Image Enhancement

    ArchiGen argues that "4K" in architectural rendering only specifies file dimensions without clarifying which geometric structures must be preserved or which defects matter. The article recommends writing a one-page output contract before downloading a ComfyUI workflow, specifying exact pixel dimensions and aspect ratio, categorizing areas as protected/editable/discardable, naming specific defects for each improvement, establishing two-tier review standards for delivery size and inspection zoom, and saving aligned originals, outputs, and difference maps as proof.

  6. ArchiGen AI · 图像生成与ComfyUI实战36

    The First Blender Model Looked Fine—Only After Audit Did It Truly Align with the Drawings

    ArchiGen used OpenAI's Codex to drive Blender 5.2.0 LTS, converting raster floor plans into models and overlaying the original images for audit. The first model was found to have 5 errors: the kitchen was positioned incorrectly, the corridor was offset by approximately 1 to 1.4 m, the bathroom door was on the wrong wall, and two extra doorways and a stair connection appeared out of nowhere.

  7. note · wise_azalea8300 · 图像视频创作分享65

    ComfyUI Video Perspective Change Workflow: Running Locally with MiniMax H3 and Angle Change LoRA

    The author released a ComfyUI workflow that uses the video generation model MiniMax H3 combined with an angle change LoRA to alter the camera perspective of existing videos, enabling wide-angle, side, low-angle, and 360° Orbit effects around a target. The workflow runs entirely locally and is free, with various techniques allowing execution in an 8GB low-VRAM environment. It supports both SFW and NSFW content, and the article includes download links and import instructions.

    Why it matters: The author published a ComfyUI workflow for changing perspectives using MiniMax H3 and an angle change LoRA, along with a local running solution for 8GB low-VRAM environments.

  8. Curious Refuge 创作教程62

    How to Generate Depth Maps with AI: A Tutorial Based on Fal and Depth Anything

    Curious Refuge published a tutorial demonstrating how to generate depth maps using Depth Anything on the Fal platform. The process involves uploading a video, selecting the VDA Large model, and rendering; in the example, a grayscale depth video was generated in approximately 60 seconds. This depth video is then used as a motion reference input for AI video generation tools that support video references, combined with a starting image and prompts to control visual style and motion structure. The article also notes that Depth Anything is open source and can be run locally on Mac to generate depth maps for free.

Oct 2Fri
  1. huobao-drama · 开源创作项目发布10

    Huobao v4.0.7 released: Unified brand icons and updated multi-platform installers

    Huobao has released v4.0.7, unifying the web logo, browser icon, and macOS and Windows application icons, and providing installers for macOS Apple Silicon, macOS Intel, and Windows x64. The macOS Apple Silicon installer has passed service and frontend startup checks, while other platforms have only completed packaging and content verification without corresponding system runtime testing.

  2. ArcReel · 公开创作项目发布50

    ArcReel v0.32.0 released: New editing view and Agent editing capabilities

    ArcReel v0.32.0 adds an editing view that can stitch and play videos along an editing timeline and render the final output locally, supporting narration, burned-in subtitles, BGM, and transitions, and can also export CapCut drafts. Agents can create and batch-edit editing timelines through the edit-video skill, and use contact sheets to view black screen, frozen frame, and shot transition point signals in footage. The "Episodes" view replaces the "Source Files" page, supporting one-click AI planning to the end as well as manual splitting, dividing, and merging.

  3. WaveSpeedAI 官方博客62

    WaveSpeedAI launches Ultimate Video Upscaler to upscale AI video to 4K

    WaveSpeedAI released Ultimate Video Upscaler, which can upscale video to 720p, 1080p, 2K or 4K; the official example upscales a 480p 5-second clip to 3840 × 2160 while keeping 24 fps and the original audio.

    Why it matters: A workflow of low-resolution drafts plus post-upscaling, combined with a cost structure priced by target resolution, can be used to evaluate trade-offs in the production pipeline.

  4. WaveSpeedAI 官方博客62

    WaveSpeedAI launches AI Cinema Studio to generate cinematic video shots with a director panel

    WaveSpeedAI launched AI Cinema Studio in the generator sidebar, using five cards—References, Film setup, Camera, Color palette and Lighting—to turn cinematic style, camera model, camera movement and lighting choices into precise shot descriptions for video models.

    Why it matters: Cinematic feel is broken down into preset panels for style, camera model, camera movement and more, letting creators judge whether this saves them the step of writing prompts.

  5. Adobe · 官方创作与影视博客22

    "KPop Demon Hunters": how Sony Pictures Imageworks used Adobe Substance 3D and After Effects to create this global hit animation

    Sony Pictures Imageworks texture lead Jody Tidsbury and motion graphics artist Nori Kaneko disclosed that the team used Adobe Substance 3D Painter, Designer, Sampler and After Effects to complete the character, costume and environment textures and the concert motion graphics for "KPop Demon Hunters."

  6. ArchiGen AI · 图像生成与ComfyUI实战22

    Veras material generator: reference images have color, but no scale

    Chaos says Veras's material generator can turn any reference image into a material, or match a material in the Cosmos library, while preserving mapping, scale and alignment. But the article points out that an unmeasured material sample is only a color reference, not a dimensional specification, and generated results may look similar while corresponding to different products. It recommends placing a ruler next to the sample before uploading, checking maps channel by channel, and verifying scale and repetition under three lighting conditions: diffuse, grazing and indoor light.

  7. ComfyUI MCP | Agent Panel · ComfyUI创作项目发布22

    ComfyUI Agent Panel resumes limited maintenance and adjusts support policy

    ComfyUI Agent Panel resumes limited maintenance of the local panel and provider selection, withdraws the October 9 shutdown commitment, keeps automatic issue reporting off, and will reassess support once Comfy's official local panel is public. On the fix side, unpacking now runs according to the reforged internal node identity and named slots, can repair misaligned connections within a single undo, rolls back when identity cannot be confirmed, and temporary provenance information is not written into saved workflows or undo history.

  8. Comfy 官方博客60

    Episode 852 Hakoniwa creates first animated short YUI with Comfy Agent

    The official Comfy blog shares YUI, the first animated short created by animation creator 852 Hakoniwa using Comfy Agent, whose protagonist's name is taken from the last three letters of ComfyUI.

    Why it matters: The animation creator completed a first short with Comfy Agent and disclosed the cost, work hours, and a shot-by-shot approach of comparing models.

Oct 1Thu
  1. note · yaoyoroztech · 图像视频创作分享30

    Two image AIs released the same week, and one's images can't be posted — Qwen-Image 2.1 and Ming-Image 0.1 differ not in performance but in license

    Two image AIs released the same week, Qwen-Image 2.1 and Ming-Image 0.1, differ not in performance but in license. Qwen-Image 2.1 was released on September 20, its drawing component is 7B, it supports transparent backgrounds and up to 10 reference images, and ComfyUI supported it on the first day of release, but it uses a research license, with commercial use requiring a separate agreement, so the author decided not to publish its generated images.