Skip to content
Date and source

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

Oct 1Thu
  1. 小智博客 · 音视频实践60

    Deploying Pixelle-Video on Windows: Generating Complete Videos Directly from a Topic

    A deployment tutorial for Pixelle-Video on Windows, with the goal of chaining scriptwriting, image sourcing, and voiceover into an automated workflow to generate a complete video directly from a topic. The original text notes that traditional short-form video production requires repeatedly switching between writing scripts, finding or generating images, adding voiceover/subtitles/background music, and editing software, with asset import and regeneration being the most time-consuming steps.

  2. 逛逛GitHub70

    Writing Code to Make Videos with Claude Opus 5.5: 10 Finished Pieces and 5 Open-Source Projects

    The way to make videos with Claude Opus 5.5 is not for the model to directly generate frames, but to have Agent tools such as Claude Code and Codex write HTML, Canvas, WebGL, or Remotion animations, then export MP4 frame by frame, with subtitles, camera paths, and transitions all adjusted in code.

    Why it matters: A video production path using Agents to write HTML, Canvas, and WebGL code and export MP4 frame by frame, with 10 finished pieces and 5 open-source projects available for reproduction.

  3. ArchiGen AI · 图像生成与ComfyUI实战22

    Why AI Rendering Rankings Change After Super-Resolution

    ArchiGen points out that current AI rendering comparisons often mix three different outputs—native generation, vendor super-resolution, and manual post-processing—into a single score, rendering image quality scores meaningless. The article recommends preserving unprocessed native files and recording pixel dimensions, format, generation mode, and seed, while separately annotating tools and parameters for each stage: generation, denoising, super-resolution, repair, color grading, and export. Native fidelity and delivery readiness should be tested separately with two scores published; if the number of protected details changes after super-resolution, fidelity is deemed non-compliant.

  4. CoAnimator · 可编辑视频与动画工作流22

    What Is an Agentic AI Video Generator?

    An agentic AI video generator refers to a video creation approach where AI agents coordinate planning shots, generating candidates, reviewing results, and assembling sequences, as opposed to simply having a model generate or transform assets based on prompts. Anthropic provided this architectural distinction when explaining predefined workflows versus dynamic agents; agentic workflows can include human review checkpoints, or autonomously complete planning, generation, evaluation, and revision after an initial brief. What the system can inspect determines the reliability of its self-review, and whether it can retain independently editable elements such as titles, recordings, narration, and timelines determines the cost of modifications.

  5. ArchiGen AI · 图像生成与ComfyUI实战22

    Stop Giving Photorealism a Single Vague Score: ArchiGen Proposes a Six-Category Defect Checklist for Rendering Quality Control

    ArchiGen proposes replacing the vague 'photorealism' score with a 'defect checklist,' breaking rendering quality control into six categories: geometry, material, lighting, reflection, scene context, and image completeness. Each item requires marking the location, describing the deviation, and stating whether it impedes the intended use. Geometry has first veto power; if geometry is wrong, one should return to the control stage to adjust inputs, masks, edges, or depth guidance and generation strength, rather than handing it off to super-resolution tools.

  6. AImorph-艾摩弗形界 · 创作者专栏50

    Top-down typographic poster ceiling! 9 sets of AI object typographic posters, every character holds a memory

    A creator used Qwen-Image 3.0 to generate 9 sets of top-down still-life typographic posters, precisely assembling words such as "graduation," "going home," "keep going," "winter break," "teacher's grace," and "back to school" from real objects like graduation caps, train tickets, 2B pencils, and chalk, with each 3:4 image paired with a sticky note to highlight the theme. The same LoRA and image templates are now available on LiblibAI, and the prompts are public for reference and derivative creation.

Sep 30Wed
  1. note · synth_brain · 图像视频创作分享65

    Three ways to make MiniMax H3 high-speed and high-resolution: Fused-Turbo-Int8, Spectrum, and Latent Upscaler

    The author shared a high-speed, high-resolution all-in-one ComfyUI workflow for MiniMax H3, the core of which is replacing the base model with the minimax-h3-fused-turbo-int8-convrot model, which integrates FL2V and Ref2VA, has a built-in 4STEP TurboLoRA and Mystic V2 LoRA that suppresses jitter and ghosting, and is about 21GB in size.

    Why it matters: The author tested MiniMax H3's model replacement and speed-up nodes, providing a comparison showing an 800×800 eight-second video dropping from 7 minutes 13 seconds to 3 minutes 37 seconds, which can be transferred to existing video production workflows.

  2. note · catap_art3d · 图像视频创作分享34

    Trying Ming Image 0.1 Design in ComfyUI

    Ming Image 0.1 Design from inclusionAI under Alibaba-affiliated Ant Group has been added to the default templates of ComfyUI 0.38.0 stable. The template calls Qwen3.8 27B by default as a prompt enhancer; 16GB VRAM will OOM, so the author switched to running it with ollama and the comfyui-ollama node. The author considers its Japanese performance average, but its censorship is looser and its freedom higher than similar tools like Ideogram.

  3. ArchiGen AI · 图像生成与ComfyUI实战60

    ComfyUI Architectural Render Repair Order: Fix Walls First, Then Reflections

    ArchiGen AI proposes breaking "making it photorealistic" into six ComfyUI repair steps ordered by dependency: camera and subject geometry, material boundaries and scale, light direction and exposure, glass and reflections, plants and set dressing, and local defects and finishing. Each step requires saving numbered checkpoints and setting acceptance anchors.

  4. 阿真Irene · 创作者专栏78

    Alibaba Open-Sources Qwen-Image-2.1: One Model Covers Image Generation, Editing and Transparent Backgrounds

    Alibaba has open-sourced the Qwen-Image-2.1 image model, with a 7B visual generation component using a 32-layer Single-Stream DiT; one model covers generation, editing and native transparent-background images.

    Why it matters: The author presents extensive hands-on cases showing Qwen-Image-2.1's performance in image generation, editing and native transparency, and provides measured speeds on consumer-grade GPUs.

Sep 29Tue
  1. LTX-2 官方发布62

    LTX-2 Releases v1.4.0, Adding Chunked Long-Video Generation and Keyframe Decoding

    LTX-2 released v1.4.0, adding --chunked to Distilled, the two-stage TI2Vid, A2Vid, Dub-It and IC-LoRA, enabling ultra-long video generation with a default 97-frame window and 25-frame carry, without needing to set --chunk-pixel-frames or --chunk-carry-frames.

    Why it matters: LTX-2 v1.4.0 lists interface changes for long-video generation, chunked decoding and HDR workflows in one place, making it easier for existing workflows to assess migration costs.

  2. Canva 官方新闻室22

    Canva Launches AI Connector for Meta's Muse, Enabling Design Generation Within Conversations

    Canva has launched an AI Connector for Meta's personal AI agent Muse, allowing Muse to hand off visual creation tasks directly to Canva. Once connected, Muse can access users' brand fonts, colors, and assets, search the design library, and export finished files, with all generated designs remaining fully editable. The feature is now available to users in the United States and Canada, with AI capabilities secured by Canva Shield.

  3. Prompt Tag Editor · ComfyUI创作项目发布38

    ComfyUI Prompt Tag Editor Update: Instant Drag Response and Persistent Tag States

    ComfyUI Prompt Tag Editor updates interaction and state management: dragging now begins instantly upon movement, with no need to long-press and wait; a single click can disable or re-enable a tag, with disabled tags turning gray and remaining in the list but excluded from the prompt. Trailing commas are preserved during input, and tag order, weight, translation, and disabled status persist after reloading.

  4. DramaClip · 公开创作工具发布80

    DramaClip v0.2.0 First Public Release: Import Short Dramas to Batch-Generate Promotional Short Videos

    DramaClip v0.2.0, the first public release, allows users to import a short drama with dozens of episodes and batch-generate ready-to-publish promotional short videos, with all media processing completed locally. This version uses OCR and ASR fusion transcription with hard-subtitle character-by-character correction—60% of segments were corrected in testing—and employs CAM++ voiceprint clustering for speaker diarization.

    Why it matters: A short-drama promotional video tool that completes transcription, narration scripts, and voice cloning locally—explore its nine output modes and cut-point alignment approach.

  5. cozdx1 Comma Weight · ComfyUI创作项目发布22

    ComfyUI Plugin comma-weight Released: Adjust Comma-Separated Prompt Weights with Ctrl+Up/Down

    The ComfyUI creation project comma-weight has been released, supporting Ctrl+Up/Down to adjust full comma-separated prompt tags or loosely selected tag groups. The plugin reuses ComfyUI's weight precision settings and preserves existing weighted groups, provides an instant toggle under Settings → Comma-Weight, and includes documentation in English, Simplified Chinese, Japanese, and Korean.

  6. ArchiGen AI · 图像生成与ComfyUI实战26

    Don't Rush to Import a ComfyUI Workflow: Read This Diagram First

    When faced with a ComfyUI architecture workflow shared by a stranger, don't blindly install dependencies just to eliminate red node errors. Instead, start by tracing the output path backward from the Save Image node to understand inputs, constraints, variations, and dependencies. The article suggests filling out a six-line 'image passport' for each workflow, recording inputs, models, controls, variations, dependencies, and outputs, and distinguishing between structural controls and visual guidance, treating dimensions as a chain to verify node by node. The first test should be run on a non-confidential proxy image at a moderate resolution. Custom nodes must be treated as software installations, with repositories, versions, and licenses recorded.

  7. drama-skills · 公开创作项目发布48

    v0.8.1 Released: Still-Frame Editing, Character Voice Binding, and Tested Prompting Methods

    The static comic drama tool v0.8.1 adds still-frame editing, allowing direct editing from keyframes and voiceover into a finished video, with support for mixed still-frame and video editing, push-pull and panning, continuous camera movement by speed, and voiceover and subtitles across cut points. The video prompt adds a reference audio field, reconciled with the character voice reference in the visual settings, compiled as reference_audio during production, and must be bound to the speaking character in the shot. This version also supplements, based on small-sample testing, prompting methods for reaction shots, two-person contact, keyframe art style, and TTS tone; the conclusions are limited to the samples and conditions in the records.

  8. Wireflow · AI短剧与视频制作教程22

    Full Breakdown of Shotstack 2026 Pricing: Plans, Credit Conversion, and Actual Costs

    Shotstack subscriptions start at $39/month including 200 credits, with 1 credit rendering 1 minute of 1080p video; pay-as-you-go packs cost as low as $0.07/minute, and subscription tiers as low as $0.045/minute. Subscription overages are billed at a 30% premium, and unused credits can roll over up to 3 times the monthly allowance; pay-as-you-go packs are valid for 1 year, and rendering stops once the balance reaches zero.

  9. Lightricks · LTX 模型71

    Lightricks Releases LTX-2.5-22B IC-LoRA Alpha Gen Matting Model

    Lightricks released IC-LoRA Alpha Gen based on LTX-2.5-22B, which takes ordinary RGB video as input and generates frame-aligned grayscale alpha mattes without green screens, masks, or prompts, and can handle semi-transparent elements such as hair, fur, smoke, fire, sheer fabric, glass, and water.

    Why it matters: It generates frame-aligned alpha mattes from ordinary video without green screens or prompts, offering a new alternative for matting and compositing workflows.

  10. GitHub:AI视频开源项目发现69

    ReelMimic Open-Sourced: Input a Reference Video to Generate Same-Style 2D Animation with Multi-Agent

    ReelMimic is an open-source project; users provide a reference video and a one-sentence request, and it breaks down editing rhythm, shot length, transitions, composition, color, and camera movement, first generating a storyboard and style-frame plan for confirmation, then handing it to up to 6 AI agents for parallel production, with each shot reviewed by another agent, and fixes requiring before-and-after comparison screenshots.

    Why it matters: A locally run multi-agent animation tool that breaks down a reference video's rhythm and camera movement into a reviewable creative plan.

  11. director-desk · 开源创作项目发布34

    Director's Console 0.4.10 Released: Adds Hand-Drawn Motion Paths and Performance Optimizations

    Director's Console 0.4.10 adds hand-drawn motion paths, supporting ground, stairs, and object surfaces, with multi-stroke continuation and undo while retaining point selection. This version optimizes dragging and timeline editing of large imported models, moves OBJ parsing, packing, and validation into a background Worker, and adds curve adjustment and range sampling for depth frames.

Sep 28Mon
  1. second-unit · 开源创作项目发布22

    Second Unit 2026.09.28 Released: Windows Version Updates Workflow Directory and Multiple Fixes

    Second Unit released version 2026.09.28, updating the Windows download to the main branch and incorporating the workflow directories and fixes added after the September 15 package. The update includes MiniMax H3, LTX 2.5, SAM 3.1, WAN 2.2, and Juggernaut workflow directories, as well as model-specific prompt extensions, environment presets, seed handling, and an H3 Pose Follow fix.

  2. HelloGitHub15

    HelloGitHub Issue 126: Claude Code status bar, hand-drawn image generation skill pack, and 31 other open-source projects

    HelloGitHub Issue 126 features 31 open-source projects, including ccstatusline for customizing the Claude Code status bar, the hand-drawn-style image generation skill pack handraw-style that can be installed into Codex, and srt-whiteboard-animation, which turns SRT subtitles into whiteboard hand-drawn videos.

  3. ArchiGen AI · 图像生成与ComfyUI实战36

    Polishing rendered images requires an AI change map: reviewing ComfyUI image-to-image with a difference matte

    Addressing the problem that ComfyUI image-to-image polishing of rendered images also alters unauthorized areas, ArchGen AI proposes adding a difference matte to each review, comparing the aligned baseline image with the candidate image pixel by pixel, darkening unchanged areas and highlighting changed pixels. The workflow includes four steps: freezing the baseline image, defining the allowed-change matte, generating the raw difference, and separating allowed from unexpected changes, plus a flicker comparison; it classifies changes into four types — requested, necessary collateral, harmless incidental, and prohibited — rather than pursuing zero difference.

  4. InvokeAI 官方发布20

    InvokeAI releases v6.14.2: fixes multiple bugs from 6.14.1, adds custom font import and krea-2 style transfer

    InvokeAI releases v6.14.2, fixing multiple bugs from 6.14.1 and adding two features: the Canvas text tool now supports importing custom fonts, and image style can be transferred to krea-2 via a reference image. This version also fixes issues with password reset tokens, path traversal protection, img2img posterization, and release of the quantized Qwen2.5-VL encoder in VRAM, and restricts Z-Image to using only the Qwen3 4B encoder.

Sep 27Sun
  1. Lightricks · LTX 模型71

    Lightricks releases the LTX-2.5-22b IC-LoRA old-film restoration model

    Lightricks releases LTX-2.5-22b-IC-LoRA-Restore on Hugging Face, an In-Context LoRA based on a reference video that renders old footage — low-resolution, low-bitrate, tape, or black-and-white/sepia scans — into clean, color, high-definition footage, removing compression damage, flicker, dirt, and scratches.

    Why it matters: Lightricks open-sources an old-film restoration LoRA, providing a two-stage workflow from 480-line scans to 4K and measured gains, which can be compared with existing restoration pipelines.

  2. GitHub:AI视频开源项目发现65

    echris6 releases motion-video-kit: a skill pack for making commercial ad films with Claude Code

    echris6 has released motion-video-kit on GitHub, a Claude Code skill (also usable as plain context for other LLMs) for producing launch-style commercials for real businesses using AI-generated assets plus code-driven motion (HTML/GSAP, optionally Three.js).

    Why it matters: This skill packages the review loop, motion grammar, and QA scripts for commercial ad films into a reusable workflow, suitable as a reference for anyone making AI ad films.

  3. Ciaro · 中文AI电影制作教程22

    How to maintain character consistency in AI video

    Character consistency in AI video is fundamentally a process problem rather than a prompt problem; character drift, prop inconsistency, and scene changes are the three core risks. A workable approach is to first break down the script, build a character bible plus prop and scene reference libraries, generate hero reference frames first and then derive shot variants, and review in batches and correct on the timeline. Ciaro Pro's asset management and character workflow can keep the script, reference images, generated frames, and edits linked together.

  4. Ciaro · 中文AI电影制作教程12

    Why AI image editors should be used for pre-production, not just content creation

    AI image editors should be treated as a controlled pre-production layer for script breakdown, shot lists, visual references, and storyboard approval, rather than a toy for generating isolated flashy images. Ciaro Pro's storyboard workspace links the script, breakdown, storyboard boards, assets, generation, and editing in a single workspace, so that character, scene, prop, and style consistency are locked in before entering video generation. Teams should start from the story rather than the prompt, and complete approval before consuming generation credits to reduce rework and waste.

  5. drama-skills · 公开创作项目发布50

    drama-skills v0.8.0 released: payoff-first adaptation and Creation Desk v2

    drama-skills has released v0.8.0, adding a "payoff-first" adaptation workflow: first rank a payoff table by audience benefit and then split into episodes, with the Episode 1 entry comparing at least three candidates, one of which is a cold open. This version adds three genre cards—system flow, rebirth/time travel, and comeback—writes camera movement shot by shot in the storyboard, adds on-screen text and sound effect rows to the edit sheet which render overlays onto the final cut, and supports the Wan 3.0 video prompt dialect (target_video_model: wan-3.0).