Skip to content
Date and source

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

Oct 13Tue
  1. note · kt_kt_89 · 图像视频创作分享22

    v0.5.70 Video Production Agent: No Need to Generate Video for Every Scene—Split Production Methods Midway

    Personal development log: The v0.5.70 video production agent no longer applies uniform video generation to all scenes, but instead splits by scene: independent generation, continuation from the last frame of the previous video, or using FFmpeg to animate still images, calling video generation AI only for necessary shots. This version introduces the Canonical Shot Brief to unify scene design, then converts separately into image and video inputs, and sets a confirmation boundary before asset generation.

  2. note · nobinlog · 图像视频创作分享22

    From A1111 to ComfyUI: Four Reasons to Migrate After Advancing in Local Image Generation

    A local image generation user who started with A1111 advises that after learning the basics in A1111, if you want to further speed things up and do workflow orchestration, you should migrate to ComfyUI. The author says A1111 is not suitable for large-batch generation, citing an instance where 200 images were still not finished by morning, with each image taking about 20 seconds, whereas ComfyUI processes images one by one in a queue and is faster. ComfyUI can also save and reuse the entire pipeline from generation to upscaling to saving; as of 2026/10/13, the author has accumulated 510 self-built workflows.

  3. note · kawakijourney_ai · 图像视频创作分享22

    ChatGPT Generates AI Beauty: Full Process and Prompts for Creating iPhone Realistic Photos of a Japanese Female College Student's After-School Day (Class Dismissal → Club → Party → Hotel) Now Public

    Japanese creator kawakijourney_ai has released the second installment of the 'A College Student's Day' series, using ChatGPT to generate a continuous series of AI photos from class dismissal, club activities, a party, to a hotel, simulating the effect of candid iPhone shots taken by a boyfriend or senior. The tutorial provides Japanese-English bilingual prompts for each scene from STEP1 to STEP5, creating 3 characters with different appearances and hairstyles, 28 images each for a total of 84, and emphasizes fixing the orientation of desks and chairs, the position of the notebook, and slight camera shake across the entire frame to preserve realism.

  4. Leeveo AI Tutorials · 创作教程与项目分享38

    A Complete Guide to Creating a 15-Second AI Video Ad from a Single Product Photo and Taking on External Orders

    An AI video ad order-taking guide for independent skincare brands, teaching you to turn a client's product photo into a 15-second vertical ad: $500 per package, including 1 product with 1 creative concept, 3 versions with different opening hooks, subtitles and CTA, 1 round of revisions, and 3 MP4 finished videos. The example target is 10 packages × $500 = $5,000 monthly income.

  5. note · maynoha · 图像视频创作分享22

    How Free Is 'Unrestricted' Portrait Generation AI? Hands-On Testing and Selection Guide for PixAI, SeaArt AI, and NovelAI

    Hands-on testing of PixAI, SeaArt AI, and NovelAI shows all three image generation services can produce mature-style illustrations such as off-shoulder gowns and deep-V slit qipaos, but 'unrestricted' does not mean rule-free. PixAI's sensitive content is visible only to the user and credits can be carried over; SeaArt AI's daily stamina resets to zero each day and some models support unlimited generation; NovelAI's Explore requires manual review and prohibits NSFW submissions. When choosing a service, you should separately verify the generatable content, public sharing scope, generation quota, and registration requirements.

  6. note · yoshida_komuin · 图像视频创作分享62

    Running MiniMax H3 on M5 Pro Mac: Settings That Cut Single Generation from 14 Minutes to 4.5 Minutes

    The author runs MiniMax H3 locally on an M5 Pro Mac with 24GB RAM for video generation, cutting single generation time from about 14 minutes to about 4 minutes 40 seconds through three adjustments: changing single clip length from 192 frames (about 8 seconds) to 124 frames (about 5.2 seconds), adding Turbo LoRA set to 6 steps, and enabling 8-bit computation with fast attention.

  7. Generative AI · 创作教程与项目分享62

    SenseNova-U1.5 hands-on test: how a small image model challenges larger rivals

    SenseNova-U1.5 is a multimodal model that combines image understanding and generation, supports native 4096 × 4096 output, and has about 8B parameters each in its understanding and generation branches. The author tested its layout and local editing capabilities, scoring 0.948 on CVTG-2K, higher than the Seedream 4.5 (0.899) in the report, and compared it on the same tasks with FLUX.2-dev 32B and Qwen-Image 20B.

  8. note · freelife_creator · 图像视频创作分享30

    Capability comparison table of five AI image generation tools: Midjourney, DALL-E, Stable Diffusion, Firefly, and Ideogram

    A comparison table outlines the differences among five AI image generation tools—Midjourney, DALL-E 3, Stable Diffusion, Adobe Firefly, and Ideogram—across six dimensions: art style, text accuracy, Japanese-language support, commercial licensing, price, and generation speed.

  9. Simon聊AI74

    Reverse-engineering Screen Studio with REA: extracting 6 auto-zoom rules and replicating them with claude code in half an hour

    The author used the open-source project REA (Reverse Engineer Anything) to break down the Mac screen recording software Screen Studio, generating an evidence map of 3,695 files in 101 seconds, then had claude code write scripts to decrypt more than 60,000 encrypted strings and read out the 6 rules behind auto-zoom.

    Why it matters: The author used REA to break down Screen Studio and had claude code replicate it, demonstrating a complete workflow combining reverse-engineering tools with an agent.

  10. note · laoyexiaoye · 图像视频创作分享27

    Seedance and Kling Japanese quick-start guide: registration, pricing, prompt writing, and commercial-use checklist

    A quick-start guide to Seedance and Kling for Japanese users, organizing public information from official websites, official blogs, and terms of use in the order of registration, pricing, prompt writing, and commercial-use confirmation, with a confirmation date of October 13, 2026. The article includes a 40-word Chinese-Japanese-English prompt comparison table, 8 purpose-specific prompt examples (Japanese-English), and a commercial-use checklist with clause sources. The author notes that hands-on comparisons of image quality, wait times, Japanese speech, and other aspects have not yet been conducted, and actual test results will be added after testing.

  11. note · great_eagle2170 · 图像视频创作分享8

    AI video for people in their 40s: a guide to making Instagram Reels with a phone (including prompts, editing, and publishing)

    A hands-on guide for AI beginners in their 40s and 50s, explaining how to complete AI video generation on a phone and publish it as Instagram Reels. Using Higgsfield, Google Gemini, and CapCut as examples, it demonstrates three types of video effects—Earth zoom-out, smoke transformation, and wall collapse—and provides prompt corrections, a 30-second Reels edit, narration and title templates, and a 7-day publishing roadmap, with the paid section priced at 500 yen.

  12. 龙爪槐守望者 · 创作者专栏60

    Netizen uses Three.js web-rendered 3D white models as AI video reference

    Netizen cellinlab proposed using AI models to output Three.js front-end code that renders geometric blocks and camera movement paths in real time in the browser, recording it into reference video and then importing it into video generation models. Author Longzhuahuai Shouwangzhe says that feeding prompts directly into AI video easily produces camera drift and limb distortion, and introducing 3D white models provides pose and spatial reference; using Blender has a learning curve, and having AI operate 3D tools consumes credits, whereas the browser approach is zero-barrier, faster and cheaper, and runs without installing plugins.

  13. AITuber · AI短视频与提示词22

    AITuber releases 25 AI rap video prompts, categorized into five styles

    AITuber compiled 25 copy-paste-ready AI rap video prompts, grouped into five styles including street cypher, animated characters, and babies and animals. Each prompt consistently includes four elements—character, scene, emotion and camera—along with a matching BPM and beat description, such as boom-bap, 80 BPM. The prompts deliberately avoid real artists, real faces and brand names.

  14. Loomance · 本地AI动画实测60

    Wan 2.2 first/last frame test: three runs with unrelated images yield three transitions

    The author ran an experiment locally on an RTX 5070 12GB using Wan 2.2's First → Last Frame mode, with a hand-drawn spotted camel-like creature as the first frame and a photorealistic apple as the last frame; the same prompt run three times produced three different transitions: placing the drawn character into the castle scene of the last frame, staying in the drawn world before a quick cut, and a slow dissolve between the two worlds.

  15. CoAnimator · 可编辑视频与动画工作流38

    Can Cursor make videos? How to use it with CoAnimator

    Cursor can make videos: it edits projects in a video project folder and calls external video tools, while CoAnimator handles scene preview and MP4 export. Before use, CoAnimator, the coa command, FFmpeg/FFprobe and the project skill must be installed; the main workflow is based on files and commands, and the optional ACP connection requires separate compatibility testing.

  16. ArchiGen AI · 图像生成与ComfyUI实战36

    Export depth maps before ComfyUI: why renderer-native depth beats estimated depth

    Architects should export renderer-native depth maps before using ComfyUI rather than relying on depth estimation models. Native depth maps directly record scene camera and surface geometry information, whereas estimated depth introduces additional interpretation error, causing problems such as disappearing mullions and flattened planes. The ControlNet 1.1 documentation confirms its depth model can directly use true depth maps output by rendering engines, and ComfyUI's official examples also warn that ControlNet does not automatically convert ordinary images into depth maps.

  17. ArchiGen AI · 图像生成与ComfyUI实战22

    A separate pass for AI vegetation: ArchiGen's ComfyUI architectural visualization vegetation mask workflow

    ArchiGen proposes treating AI vegetation as an independent masked local pass rather than handling it together with global enhancement prompts, to protect buildings, paths and key sightlines from being altered. The approach is to mask-repaint only the planting areas, excluding facades, eaves, door openings and ramps from the editable mask, and to split foreground vegetation and building edges into two masks when necessary. After generation, species characteristics, mature scale, silhouettes, circulation and shadows must be checked, and difference overlays used to inspect where branches touch eaves and curtain walls.

  18. Synthesia · 官方博客22

    Best AI training and onboarding video tools of 2026: Synthesia, Colossyan, HeyGen, Elai, Vyond compared

    Synthesia was rated the top AI video tool for enterprise training and onboarding scenarios in 2026, followed by Colossyan, HeyGen, Elai and Vyond. Synthesia's Enterprise plan offers unlimited duration, but SCORM and glossary features require the Enterprise plan; HeyGen suits translating existing live-action footage, with the Creator plan at $29/month and the Business plan at $149/month plus $20 per seat.

  19. Hugging Face Daily Papers12

    Scaling online optimal transport minibatches to improve flow matching training stability

    Researchers propose a scalable approximation of online entropic optimal transport that substantially increases the pairing batch size between source samples and data in flow matching training while retaining the benefits of optimal transport. They theoretically prove that the method strictly reduces full stochastic gradient variance and integration error in both the unregularized and entropy-regularized cases, and that the improvement grows as the online coupling batch size increases. Experiments on single-cell gene interpolation flows and image flow training verify that larger online coupling consistently improves training stability and final generation performance.

  20. note · koza_kura3 · 图像视频创作分享10

    1.5 hours on weekday nights is enough: how tired office workers can finish their first AI animation

    For office workers who can only spare 1 to 1.5 hours on weekdays, one AI animation approach splits the process into one step per day: Monday, 15 minutes to pick a theme; Tuesday, 30 minutes to generate one character image; Wednesday, 30 minutes to add 3 to 5 seconds of motion to the image; Thursday, 30 minutes to layer in BGM or sound effects and save; Friday, review the result. The first work passes if it moves for 3 seconds and plays through completely; there is no need to pursue perfection, and completion within 14 days or generating income is not guaranteed.

Oct 12Mon
  1. TelosCompass · note AI视频创作实践34

    Making Product AI Videos with DomoAI: Write the Surrounding Motion First, Then Move the Product

    When generating product videos from photos with DomoAI, you should first write the motion of surrounding elements such as light, shadows, and steam, then decide whether the product itself moves. DomoAI's official blog suggests that products with dense text labels are best kept completely still, and if rotation is needed, keep it within 15 degrees and specify the stopping position; for scenes with people, keep only one action and clearly state the speed and pose.

  2. note · abcxy · 图像视频创作分享50

    For Complete Beginners: A Tutorial on Generating Video from a Single Image with MiniMax H3

    MiniMax H3 is a video generation AI model released by MiniMax in July 2026; it can generate video and audio simultaneously (including Japanese dialogue) and supports Turbo LoRA to reduce generation steps. In ComfyUI 0.30.0 and above, using the official template, you can generate a short video from a single image by simply placing the image (first frame) and describing the motion with a prompt, making it suitable for complete beginners.

  3. note · hatano_yusuke · 图像视频创作分享22

    3 shortcuts for automatically generating video with generative AI

    There are three shortcuts for building video generation applications with generative AI: directly integrating commercial video generation APIs such as Sora, Runway, Luma, and Pika; self-hosting open-source models such as Stable Video Diffusion with cloud GPUs; or using iPaaS and no-code tools to string together an automated pipeline of text generation, video generation, and speech synthesis APIs. Each of the three involves trade-offs in development speed, cost, and customizability. You can first use APIs or no-code tools to quickly build a prototype, then migrate to a self-hosted pipeline as needed.

  4. note · wise_azalea8300 · 图像视频创作分享78

    Comparison of 44 ComfyUI video upscaling and restoration methods, with an all-in-one comparison workflow

    The author compared 44 video upscaling and restoration methods on ComfyUI, all running locally for free, and distinguished between two scenarios: restoration and upscaling. Restoration targets low-quality footage from small cameras, surveillance, and the like, while upscaling targets upgrading HD to FHD, 4K, and 8K and recovering skin texture and eyelash detail. The article releases a large-scale comparison workflow that can run all 44 methods in one go, making it easy to pick suitable methods for different content such as people, landscapes, or animation.

    Why it matters: The author separates the two needs of restoration and upscaling, uses the same footage to compare 44 methods side by side, and releases a ComfyUI workflow that can run in one click.

  5. note · hatano_yusuke · 图像视频创作分享20

    Hyperframes video generation pitfall guide: 5 key points

    When developing an AI video generation application with Hyperframes, you can reduce pitfalls in five areas: validate early with low resolution and short frame counts, then scale up gradually; fix seed values and use control networks to maintain consistency between frames; keep prompts concise and set negative prompts; use asynchronous processing, queues, and retries to handle API timeouts and rate limits; and pin model and dependency versions and verify updates in a test environment.

  6. note · major_myrtle6198 · 图像视频创作分享22

    Running MiniMax H3/h3.c at maximum quality with no quantization on an M1 Max 64GB

    On an M1 Max (64GB) Mac, the author ran h3.c, the C port of MiniMax H3, in BF16 with no quantization, successfully generating a 10-second video without triggering out-of-memory (swap), but it took 43.2 hours. The full model is about 134GB and requires about 150GB of available storage, reading and computing in chunks from the SSD via an SSD streaming mechanism.

  7. note · 7god_ebisu8g2sdr · 图像视频创作分享22

    Even PC beginners can use ChatGPT to make AI videos while chatting: from PixVerse prompts to a YouTube Shorts hands-on

    A PC beginner used ChatGPT to generate and revise PixVerse prompts to make a 5-second vertical ASMR video of a glass pumpkin cutter. The prompt ChatGPT initially gave was too long and did not work well in PixVerse, so the author directly gave the feedback "the prompt is too long," and ChatGPT promptly produced a short version containing key points such as "transparent orange glass pumpkin on a wooden cutting board, macro close-up."

  8. note · takah_note · 图像视频创作分享8

    Online Course | Real AI Video Production That Includes Failure

    A creator shares real experience making online course videos with AI: dubbing with a voice clone of their own voice, but after recording 4 versions with emotional ups and downs, no difference could be heard, so they ultimately kept the original voice and instead created a lively feel through writing techniques such as ending with questions.