Skip to content
Date and source

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

Oct 7Wed
  1. QwenVL-Mod: Enhanced Vision-Language · ComfyUI创作项目发布28

    ComfyUI-QwenVL-Mod Update: Cleans Up GGUF/HF Model Directories and Fixes MiniMax Presets

    ComfyUI-QwenVL-Mod has cleaned up the GGUF and HF model directories, keeping three vision-language (VL)-capable DavidAU heretic models per backend (4B / 9B / 27B), all verified as image-text-to-text with working mmproj files, and removed text-only duplicates and the mislabeled "3.8-9B" entry.

  2. CGPress67

    ComfyUI Launches AI Agent Comfy Agent

    Comfy has launched Comfy Agent, an AI assistant for its open-source node-based generative AI platform that can plan, build, and fix ComfyUI workflows on the canvas. After users describe what they want to make, the agent connects nodes, wires up models, and debugs the parts that go wrong; it currently runs on Comfy Cloud, with a local version coming soon.

    Why it matters: ComfyUI brings an agent onto the canvas that can automatically build nodes, connect models, and troubleshoot, so creators can judge whether the way they build workflows needs to change.

  3. X搜索:AI视频开源项目发现22

    Comfy Dev Platform Challenge Registration Opens

    The models are open source, but the apps that use them are not. Our ask to you? Support open-source creativity by rebuilding a paid creative feature in a public setting, with a chance to win $10,000 Submit your work by 9 AM PT on Monday 10/19 for the Open Call: Comfy Dev Platform Challenge! Powered by @NVIDIA @Runpod Open-source ecosystem partners @LTX @BFL $10,000 grand prize 3 NVIDIA RTX 5090s Additional prizes from LTX and Flux Free credits for the first 100 registrants

Oct 6Tue
  1. X搜索:AI视频开源项目发现58

    Node Banana 2.0 Released: Supports ComfyUI Workflow Nodes and Claude, Codex Subscriptions

    Node Banana 2.0 has been released, which the author calls the project's biggest version update yet, still 100% free, open source, and supporting bring-your-own key. The new version can be downloaded directly with no more git hassle, has a built-in agent that uses a Claude or Codex subscription, and supports using ComfyUI workflows as nodes, with an overall bottom-up redesign.

  2. Hedra 官方博客60

    Hedra Launches Developer API: One Key to Access 110+ Generative Models

    Hedra launches its Developer API, allowing access to 110+ generative models with a single API key and prepaid USD wallet, covering video, image, audio, and text, including Veo 3.1, Kling V3, Seedance 2.5, MiniMax H3, Nano Banana Pro, ElevenLabs V3, and more.

    Why it matters: Hedra consolidates 110+ video, image, audio, and text models into a single API and prepaid wallet, enabling developers to evaluate the integration costs of multi-model pipelines.

  3. yanhuo-easy-use · ComfyUI创作项目发布12

    yanhuo-easy-use Fixes False Flagged Issue in 1.3.0 and Adds Pre-Publish Self-Check Script

    yanhuo-easy-use fixes the issue where version 1.3.0 was flagged: a YARA rule mistakenly identified the JS Function binding syntax in web/js as a Python socket binding, so Reflect.apply was used instead to eliminate the literal string. A pre-publish self-check script tools/check_publish_hygiene.py has also been added.

  4. Podcastle36

    Best AI Video Editors of 2026: 10 Tools Compared on Real Editing Tasks

    Podcastle tested 5 AI video editors using the same 95.9-second messy talking-head clip. Async completed filler-word removal, pause removal, dead-take deletion, audio cleanup, subtitle addition, B-roll generation, and 9:16 conversion with a single prompt, producing a 62.9-second final cut with the best overall performance. Descript completed the full workflow in about 8 minutes, removing 10 of 11 filler words, with better vertical reformatting results.

  5. あいきみ · 图像编辑与LoRA实测58

    RTX 3090 Hands-On with MiniMax H3's 360° Orbit LoRA: Generating Orbit Videos from a Single Image

    The author tested pablodawson's MiniMax H3 360° Orbit LoRA on an RTX 3090, using the same image as both the first and last frame of the video, generating an approximately 3-second, 73-frame orbit video. The back of the subject, not captured in the original image, appears midway through.

  6. 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.

  7. ArchiGen AI · 图像生成与ComfyUI实战22

    Giving Renderers a Normal Bad Input: A Weak-Input Benchmarking Method for AI Renderers

    ArchiGen proposes testing AI renderers using the weakest source images a studio can normally accept, fixing the camera and key design facts, and performing only one initial generation and one controlled revision. The method requires producing five frames: an acceptable source image, default first pass, controlled fix, delivery export, and a difference overlay, scored by the number of changed invariants, first usable output, and fix time. The article cites Rendero's comparison of 11 AI rendering products, noting that Rendero did not actually execute this test.

  8. GitHub:AI视频开源项目发现65

    mushigaite open-sources short-video-maker: automatically cuts YouTube long videos into vertical short videos

    mushigaite has open-sourced short-video-maker on GitHub, which can automatically cut YouTube videos or local files into 9:16 vertical short videos, integrating highlight detection, subtitles, translation and voiceover, with no intro credits or watermarks.

    Why it matters: The open-source project strings long-video slicing, subtitles, translation and voiceover into a single local pipeline, and can serve as a free alternative reference for short-drama overseas editing tools.

  9. 阡陌的小站 · 本地创作实战70

    Tutorial: deploying Qwen-Image-2.1 and MiniMax H3 locally in ComfyUI with 8GB VRAM

    Qianmo published a tutorial on generating images and videos locally via ComfyUI on an RTX 4070 Laptop with about 8GB VRAM, using the Qwen-Image-2.1 jailbreak GGUF workflow for images and MiniMax H3's 04_i2v_fl2v_4step_sla_lowvram workflow for videos.

    Why it matters: A complete path to running Qwen-Image-2.1 and MiniMax H3 under 8GB VRAM, including model files, directory structure and parameter configuration, reproducible by comparison.

  10. huobao-drama · 开源创作项目发布17

    huobao-drama v4.0.8 released: quick configuration supports domestic/international node selection

    huobao-drama v4.0.8's quick configuration adds domestic/international node selection, defaulting to follow the interface language: Chinese corresponds to firemux.cn, other languages to firemux.com. The one-click recommended configuration and the Key acquisition link are generated according to the selected node.

Oct 5Mon
  1. ComeCut · 开源创作项目发布18

    ComeCut resource pack v1.0 released

    ComeCut released resource pack v1.0, containing three files: ffmpeg-win-x64.zip provides the FFmpeg calling library, models.zip provides the local models required by specific features, and onnxruntime-win-x64.zip provides the model inference environment.

  2. 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.

  3. CoAnimator · 可编辑视频与动画工作流22

    The 7 levels of Agentic AI video creation: from manual editing to agents maintaining projects

    CoAnimator proposes a 7-level framework for Agentic AI video creation, from manual editing, AI-assisted tasks, prompt generation, and predefined workflows, to level 5 where the agent leads editing, level 6 where the agent checks and revises, and level 7 where the agent maintains saved projects. The framework distinguishes workflows from agents across three dimensions: decision authority, result checking, and maintainability, and uses a 40-second product demo update as an example to illustrate the differences in responsibility at each level.

  4. H3 Temporal Sampler · ComfyUI创作项目发布43

    ComfyUI H3 Temporal Sampler v1.5 released: renamed and adds Seam Lock multi-frame gradient freeze

    The ComfyUI creative project H3 Temporal Sampler released v1.5, renamed from its original name to H3 Temporal Sampler, and added the Seam Lock multi-frame gradient freeze feature. This version also updates default parameters: Smart Bounds off, Overlap set to 5, Blend using multiband, and Seam Lock Frames set to 2.

Oct 4Sun
  1. InvokeAI 官方发布62

    InvokeAI 7.0.0 alpha 1 released: all-new workbench, canvas engine, and video panel

    InvokeAI released 7.0.0 alpha 1, calling it its largest update ever, with about 320 PRs and 2,600 commits, requiring Python 3.12, and with the new interface as default.

    Why it matters: InvokeAI 7 integrates canvas, workflows, and video generation into a single workbench, and adds support for models such as MiniMax H3 and LTX-2.5, which can be used to judge whether to migrate an existing image generation workflow.

  2. note · hideout927 · 图像视频创作分享40

    Generating character design sheets with MiniMax H3 in ComfyUI: no dedicated LoRA needed

    MiniMax H3 can leverage its own reference image and prompt comprehension capabilities to generate character design sheets in ComfyUI without a dedicated LoRA or additional training; generation uses Core nodes, and custom nodes only handle generating JSON and natural-language prompts. The node combines view instructions such as front, side, back, and facial close-up with the original image to keep the same character and clothing consistent, with H3 filling in parts not photographed. Japanese prompts perform worse, while English prompts pass more easily; if separate hand and foot images are not needed, this feature can be turned off.

  3. note · aoao_ai · 图像视频创作分享50

    AI comic backgrounds always inconsistent? A practical method for fixing room layout with a "background setting sheet"

    When drawing manga with AI, the positions of doors and windows, furniture layouts, and room sizes change every time the same "home" or "nursery" is generated. To address this, the author created a "background settings sheet" independent of the character settings sheet, recording basic layouts such as location type, door/window and large furniture positions, and room relationships, along with composition and description rules—for example, never using a frontal composition for the entryway, fixing the refrigerator position, and fixing equipment like the nursery slide. Small items and items that appear only in a given episode are not included in this sheet and are managed on the script side; the settings sheet is fed directly to the image generation AI rather than being rewritten into prompts each time.