Skip to content
Date and source

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

Oct 12Mon
  1. SuSu_酥酥36

    Fable 5.5 Generates a Poetic Animation in Claude Code in 2.5 Hours

    Fable 5.5, in gray release, works almost entirely code-driven in Claude Code, producing a poetic animation in 2.5 hours, with art direction, style, pacing and storyboard all decided by the model itself. The work is based on imagery from Laufey's "Promise" and "5 Centimeters per Second," featuring a hand-drawn brushstroke opening, subtitles in Chinese, English and Japanese, and a dot-matrix map shot of a 7.18m walk; only some images and music are external assets.

  2. 黯马aigc · 创作者专栏34

    Hands-On with Higgsfield and GrandAI: A Full Review of Two Niche AI Image Generation Sites

    The author hands-on tested two niche AI image generation sites, Higgsfield and GrandAI, walking through basic introductions, page features and actual image generation examples. The content is presented as a complete hands-on tutorial, using multiple cases to show each site's image generation characteristics as a reference for new tools for users who regularly make images with AI.

Oct 11Sun
  1. z-ab · 开源短剧与创作项目分享74

    Lanshu open-sources Agent Skill lanshu-create-ai-presenter-video: a digital human video from one authorized photo, with 9 built-in styles

    Lanshu open-sourced Agent Skill lanshu-create-ai-presenter-video; in Claude Code, Codex, Gemini CLI, Cursor, and OpenCode, a single sentence runs the entire process of script, voiceover, digital human generation, lip-sync, subtitles, editing, rendering, and quality check. The repository has 2.6k Stars, 404 Forks, and an MIT license.

    Why it matters: An Agent Skill that breaks AI video production into computable states and paid gates; its workflow design approach can be transferred to other content pipelines.

  2. z-ab · 开源短剧与创作项目分享71

    OpenBMB releases VoxCPM2: a tokenizer-free TTS model supporting 30 languages and voice design

    OpenBMB released VoxCPM2, which removes the discrete token quantization step of mainstream TTS and instead uses a diffusion autoregressive architecture to generate speech in a continuous audio latent space; the repository has 38.7k Stars, an Apache-2.0 license, and fully open weights and code for commercial use.

    Why it matters: VoxCPM2 removes discrete token quantization and instead generates speech in a continuous latent space, and offers multiple deployment paths from local to production.

  3. InvokeAI 官方发布22

    InvokeAI 7.0.0 alpha 2 released: multi-canvas projects and MySQL support

    InvokeAI 7.0.0 alpha 2 is released, adding multi-canvas projects, a MySQL/MariaDB high-performance database backend, GGUF transformers support for krea2/ideogram4/ernie-image, and the Atlas Cloud image service provider. After upgrading the database, this version cannot be rolled back to v6; the official recommendation is to create a new root directory for trial use, and a new reserve_vram_gb setting has been added to mitigate OOM.

  4. note · shio_batapopcorn · 图像视频创作分享22

    Alien Bonnie uses SkyProduction to turn everyday life into AI video

    The alien character Bonnie tested the AI video production platform SkyProduction, using the three features "Smart Canvas," "Storyboard," and "Video" to complete an approximately 40–50 second short film with 8 scenes. Video generation used Seedance 2.5 and image generation used Seedream 5.0; a single image costs 2 credits, and a 5-second video costs 50 credits, outputting 9:16 vertical 720P with audio.

  5. note · palealloy · 图像视频创作分享38

    ComfyUI Hand-Drawn Node: Draw Directly on the Node and Feed into ControlNet

    A developer created a custom ComfyUI node that allows hand-drawing directly on the node, then feeding the result into ControlNet for composition control. The author notes that prompts like "from side" are difficult to control for character orientation and gun-holding poses; hand-drawing fixes the composition and reduces randomness, and even extreme biased compositions are achievable. The node is publicly available with a workflow, and only requires LineArt-level control capability.

  6. Fstoppers22

    Hands-On Test of Photoshop AI Assisted Editor on Galaxy Photos: Results and Risks

    Photoshop 27.10's AI Assisted Editor, released on August 31, allows direct photo editing with natural language prompts. In testing on galaxy photos, the first result was natural, but the second was noticeably over-processed. This mode toggles alongside Pro Editor; when switching back, AI edits are added as a new layer, making it non-destructive. However, pixel-level comparison revealed that faint stars were added, shifted, or disappeared between different generations, making it unsuitable for news or submission use.

Oct 10Sat
  1. note · ryou_gethu93 · 图像视频创作分享12

    AI Manga: Not a Bicycle Race, and No Love Story

    At tomi's request, the author used AI to turn their old story of riding a bike to buy oden ingredients in the autumn of their second year of middle school — when they couldn't brake on a downhill and had to hard-brake with their left foot — into a manga. The inspiration came from tomi's article about a 3m bicycle dive, along with related articles by ろくねこ and Kagaya. The author says AI manga is easier to draw than expected and that self-created characters are very convenient.

  2. GitHub:AI视频开源项目发现71

    Sitor AI open-sources Frametell: generate a 1080p explainer video from one sentence or one document

    Sitor AI has open-sourced Frametell (帧言) on GitHub, which can turn a sentence, document, PDF, slide deck, or image into a 1080p explainer video with subtitles. In the workflow, a director agent first produces a storyboard for confirmation, then writes narration, dubs it with ElevenLabs (Volcano Engine TTS for Chinese), draws page by page and self-checks, and includes five built-in styles: warm-story, study, chalkboard, whiteboard, and tech-dark.

    Why it matters: An open-source, locally run explainer-video generation tool that first produces a storyboard for confirmation and then dubs and renders, so creators can use it to assess whether to add it to their production workflow.

  3. SuSu_酥酥58

    MiniMax Design integrates Opus 5.5, generating code animations from a one-sentence prompt

    MiniMax Design has integrated Opus 5.5, and the author says a one-sentence prompt can directly generate code animations that can then be further modified. In the interface, the model can be selected as Gamma-Op 5.5, supporting JS animations, motion graphics, knowledge explainers, and Web/UI demos; the author rates it as fast and moderately priced.

  4. z-ab · 开源短剧与创作项目分享62

    awesome-claude-video-skills collects 268 agent video skills and assigns each a safety rating

    awesome-claude-video-skills collects 268 open-source projects that let coding agents make videos, divided into 10 categories by use such as frameworks and toolboxes, product promos, knowledge explainers, editing, and vertical short videos. Each project is marked with a SAFE or CAUTION safety rating, audited by Agent Skills Hub, and the list refreshes every 8 hours.

  5. 短剧新圈 · 澎湃商业与内容趋势61

    The dead end of action scenes in AI short dramas, and Wanxing Drama Factory's 'white model' solution.

    Wanxing Drama Factory has launched a 'white model' video conversion capability that converts original videos into untextured 3D minimalist model videos, preserving action, positioning, timing, and camera movement, achieving nearly 100% model compliance for complex action scenes; simultaneously upgraded TGI2.5, with generation speed improved by more than 50%, and the price for 2K standard quality reduced from 7 credits to 2 credits.

  6. note · cocoredo_2509 · 图像视频创作分享56

    Claude Motion is not a video generation AI, but an editable animation feature

    Anthropic released Claude Motion in Beta form on October 8. It can turn materials, charts, and explanatory text into short animated videos and export MP4. The official description states that it does not use a video generation model, but instead generates code that drives text, graphics, charts, and images, so numbers, display durations, and title order can be modified without regenerating the entire segment.

  7. Wireflow · AI短剧与视频制作教程29

    Figma Weave vs. ComfyUI: which to use in 2026

    The core difference between Figma Weave (formerly Weavy) and ComfyUI is the contest between a hosted canvas and a local canvas: the former uses credits in the browser to call commercial models such as Google, OpenAI, Kling, and Runway, while the latter is GPL-3.0 open-source software that runs on your own GPU.

  8. note · 2tm · 图像视频创作分享22

    Fully automated, free production of AI animation and four-panel comics with MiniMax H3

    A creator used MiniMax H3 in a Linux environment to fully automatically generate AI animation and four-panel comics, with hardware consisting of an RTX Pro 2000 Blackwell with 16GB VRAM, an AMD Epyc CPU, and 48GB of memory. The work "Kurochi to Paka" tells a short story about a black cat and an alpaca, and a short animated version was also released on YouTube.

  9. Curious Refuge film gallery28

    HERO: Nikita Martines' AI fantasy short film

    Nikita Martines presents the AI fantasy short film "HERO," about the son of a legendary demon-hunting family preparing to inherit a mission revered by his village for generations. The film is a Higgsfield Global Film Festival project that moves from grand fairy-tale-style narration to a tense confrontation interrogating "the price of becoming a hero."

  10. Curious Refuge film gallery42

    AI short film "The Palace": a century of mother and daughter in one cinema

    The AI short film "The Palace," created by FILMS FROM NOWHERE, tells the story of Helena Kowalski and her daughter Zofia, who remain in the same cinema from 1927 to 2026, across a century. The entire film is shot on a fixed tripod using only practical light, has only six lines of dialogue, and never shows the screen, instead placing its cinematic quality on the faces of the audience gazing upward in the dark.

  11. Curious Refuge film gallery27

    AFIFI Studio's AI short film "DECRETUM I": AJ, a boy shunned by his village, searches for himself

    AFIFI Studio presents the AI fantasy short film "DECRETUM I," telling the story of AJ, a boy feared and shunned by his village because of his strange eyes and unknown origins. With gloomy village scenes, supernatural imagery, and a mythic coming-of-age tone, the film turns an abandoned child's search for identity into an atmospheric meditation on whether fate can be chosen.

  12. 歸藏18

    Taking the chance to marvel again at how generous old Musk is! These past few days I've been frantically using Grok to make videos (code-related videos), and looking at it, I've only used 15% of the weekly quota. This is the Grok membership I bought for $99 earlier.

    Taking the chance to marvel again at how generous old Musk is! These past few days I've been frantically using Grok to make videos (code-related videos), and looking at it, I've only used 15% of the weekly quota. This is the Grok membership I bought for $99 earlier.

Oct 9Fri
  1. BlenderNation58

    UNOMi brings AI lip-sync technology to Blender

    UNOMi has officially brought AI lip-sync technology to Blender, automatically analyzing dialogue and generating character lip animation, reducing the manual work required for traditional facial animation. The integration currently supports English, Spanish, Mandarin, Portuguese, French, German, Korean, and Russian, with more languages planned. UNOMi says the goal is to make professional character animation faster and more accessible while preserving animators' control over character creation.

  2. pixaroma · YouTube 创作视频17

    "Out of Memory": a song for ComfyUI

    Pixaroma releases the music video "Out of Memory," a whole song built around ComfyUI, with all footage recorded in real ComfyUI, including real workflows, live previews, out-of-memory errors, missing nodes, and the process of repairing a corrupted VAE from the logs.

  3. sd-webui-infinite-image-browsing · 开源创作项目发布15

    sd-webui-infinite-image-browsing v1.9.1 released

    sd-webui-infinite-image-browsing released v1.9.1, adding a unified preview popup for non-media files and adding video duration badges and tag filtering (AND) to fuzzy search. This version also fixes a first-launch error and improves the sidecar file anti-orphaning mechanism and caches the unpacking process.

  4. note · atelieraika · 图像视频创作分享29

    PROMPICKS: a Windows app that combines the desired picture from 5,000 tags and generates English prompts from Japanese tags

    PROMPICKS is a Windows image-generation assistant app containing 4,874 positive tags and 126 negative tags, 5,000 in total, and supports combining Japanese tags to produce English prompts. It can connect to ComfyUI to execute generation and preview directly, is compatible with checkpoint and diffusion model split structures, and supports up to 3 LoRAs in a standard split workflow. It is priced at 1,500 yen as a portable ZIP version, and the product itself does not include ComfyUI or generation models.