Skip to content
Date and source

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

Oct 11Sun
  1. Kapwing 创作指南62

    How to Make Vox-Style Collage Animation with AI: A Step-by-Step Guide

    Kapwing published a step-by-step guide on using AI to generate Vox-style collage animation documentaries, broken into six steps: writing the script, breaking down visual beats, generating collage images, frame-by-frame animation, generating voiceover, and editing the final cut.

    Why it matters: A complete breakdown of the six-step AI workflow for Vox-style collage documentaries, including reusable image and animation prompts, ideal for creators looking to replicate the visual style.

  2. 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.

  3. Digital Camera World22

    iStock Claims "Always AI Free" Yet Encourages Users to Modify Images with AI

    iStock, under Getty Images, boasts "always AI free" on its homepage and does not allow AI-generated images in its library. However, once users purchase a photo, they can use the AI modification bar labeled "customise this image" on the page, entering text commands to alter the image — for example, changing plants to green or a bathtub to bright pink. Its "Remove Background" button does not perform well on scenes like kitchens.

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

    Midjourney V8.2: How to Create Shiny, Cute Fairy Art with a 4-Word Prompt

    Midjourney V8.2 only needs the 4-word prompt "a beautiful fairy, collage" combined with the Style Reference feature to generate shiny fairy illustrations in various styles. The author used 6 past works as references — peacock, fountain, kimono woman, owl, goldfish, and garden — with the exact same prompt; only changing the personalization code alters the visual output.

  3. note · dreamy_quail9288 · 图像视频创作分享28

    Using "rejuvenation" and "future growth" prompts to generate a 3×3 nine-grid of a life

    The sharer gives two reusable image-generation prompts: one reverse-restores the current photo back to childhood, and the other advances step by step from the current age to around 45, both outputting a 3×3 nine-grid with each image at 9:16, simulating an old photo album and a future camera roll. The author used the latter to generate a 45-year-old "オガワ" and made a three-person interview video based on it; no character speaks throughout the film, and the narrative is carried entirely by expressions and relationships between the characters.

  4. 开源中国68

    Nine practical uses of Nano Banana 2.1 with complete prompts

    Google released Nano Banana 2.1 on October 6, 2026, switching the base to Gemini 3.6 Flash and bringing capabilities such as multi-reference-image consistency, complex local editing, and text posters down to Flash's cost and speed. The article compiles nine practical uses, covering everything from multi-image consistency to image feeding, with complete prompts.

    Why it matters: Nine practical uses and complete prompts organized around Nano Banana 2.1, which can be used to assess an image-generation workflow against capabilities such as multi-image consistency and local editing.

  5. 开源中国62

    Nano Banana 2.1 in-depth hands-on: 4K direct output and Chinese typography improve, but consecutive image edits still have pitfalls

    Google updated its image-generation model Nano Banana to 2.1 on October 6, switching the base to Gemini 3.6 Flash, with upgrades focused on four areas: visual design, mask editing, subject consistency, and image realism. Hands-on testing shows the image quality supports 4K direct output from the original image with solid macro detail, and the clarity and typography of Chinese text have also improved noticeably, but the consecutive image-editing step still has pitfalls to watch for.

  6. note · lef_works · 图像视频创作分享3

    AI illustration "Soft and Cute Calico Cat" — for everyone's photo gallery

    The creator "惰眠がしたい赤猫さん" has added several variants of the AI illustration "Soft and Cute Calico Cat" to "everyone's photo gallery," including three versions: "ごろにゃん??", "ごろにゃん???", and "ごろにゃん". The works can be found with the search terms "ゆるふわ三毛猫さん" and "惰眠がしたい赤猫さん," and the same series also has LINE stickers.

  7. ArchiGen AI · 图像生成与ComfyUI实战53

    What to do when renders look too flat: use Depth Anything 3 to infer depth and feed it into ComfyUI for control

    Depth Anything 3 can estimate a usable relative depth map from a single flat architectural render, providing structural guidance for ComfyUI, but it cannot restore precise dimensions or occluded surfaces. The article provides a recovery workflow: keep the original image and the original depth map, connect a depth-compatible ControlNet and an image-to-image path, start from lower denoising and control strength, and first use a false-color preview to check depth boundaries at glass, thin rods, repeated bays, and large flat areas.

  8. ArchiGen AI · 图像生成与ComfyUI实战40

    Veras 4.5's Smart Selection can select walls with one click, but boundaries still need manual checking

    Chaos introduced Smart Selection in Veras 4.5, supporting one-click selection of targets by object, material, category, and custom prompts, driving Modify and Replace operations without mask brushes, and covering the Web version as well as integrations such as Revit, Rhino, SketchUp, and Enscape.

  9. note · ample_pika7429 · 图像视频创作分享20

    Overseas AI tool briefing: OpenAI discloses a case where AI Agent cost dropped to 1/76, Midjourney tests Thinking Mode

    OpenAI disclosed the Asana case: after analyzing the browser Agent with GPT-6 Astra, it switched to GPT-6.1 Sol for optimization, reducing the model cost per execution to $0.47 and the time to about 4 minutes, with cost improved by up to 76 times and speed by about 5 times.

Oct 9Fri
  1. Leeveo AI Tutorials · 创作教程与项目分享38

    Using AI to turn a single movie scene into an 8-panel cinematic storyboard

    A creator used AI image generation to turn an Indiana Jones–style ancient temple escape scene into a single 8-panel continuous storyboard, with each panel labeled with shot size, lens focal length, camera movement, action description, and estimated duration, plus environment references to maintain visual consistency. The workflow emphasizes breaking down dramatic beats with a director's mindset and protecting character and scene continuity, and can be used for previsualization before AI video generation with tools such as Google Veo and Kling. The author notes that the final output still requires manual correction of text, continuity, and shot specifications, and the full prompts are available only to paid subscribers.

  2. SuSu_酥酥66

    Alibaba Tongyi open-sources Qwen-Image-2.1-Turbo, producing 2K images in 8 steps

    Alibaba's Tongyi open-sources Qwen-Image-2.1-Turbo, an accelerated checkpoint based on Qwen-Image-2.1 that uses the same 7B visual generation architecture; text-to-image and natural-language editing require only 8 denoising steps, and the official release says it can still generate 2K images and supports continuous editing such as adding accessories and changing scenes.

    Why it matters: Qwen-Image-2.1-Turbo achieves 2K text-to-image and natural-language editing with 8 denoising steps, and offers two onboarding paths: Diffusers and API.

  3. あいきみ · 图像编辑与LoRA实测38

    Iris-3B joins Aikimi Forge Neo: measured comparison of the standard version, INT8, and W4A8 on an RTX 3090

    Iris-3B has been added to Aikimi Forge Neo, with a comparison of three precisions—standard, INT8, and W4A8—on an RTX 3090. For 832×1280 portrait image generation, peak VRAM was 19.10GiB for the standard version, 10.89GiB for INT8, and 9.71GiB for W4A8; W4A8 saves more VRAM but increases graininess and detail differences, and the default precision is set to INT8.

  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.

  5. ElevenLabs 产品与研究56

    ElevenLabs launches Brand Kit brand toolkit in ElevenCreative

    ElevenLabs launched Brand Kit in ElevenCreative, extracting brand visual guidelines from prompts and managing them as a single object in the workspace. Users can store colors, fonts, logos, reference images, and brand usage rules, and call them by typing @ in prompts in Image & Video, Flows, and the ElevenCreative agent; the same kit applies across all features.

  6. note · pixolm_ai · 图像视频创作分享38

    AI portrait camera settings: three examples with 24mm, 85mm, and macro

    The Pixolm developer used a red kyusu teapot as the subject and generated three AI images with GPT Image 2.5 in free creation, demonstrating three camera settings and compositions: a 24mm f/11 spatial panorama, an 85mm f/1.2 product close-up, and a 100mm macro f/8 material detail. All three images were generated on September 13, 2026, all at 2K, High, 1:1, background Auto, with camera settings enabled and no reference images, without retouching or cropping, and the actual English prompts used are included.

  7. note · tidaa · 图像视频创作分享34

    Gemini Omni tutorial (composition edition): a complete beginner uses a 5-shot storyboard to take on a 15-second refreshing beverage CM

    A complete beginner used Google's video generation AI "Gemini Omni" together with Midjourney to make a 15-second refreshing beverage web CM, using a "15-second, 5-shot golden relay" storyboard: 0-3 seconds extreme macro close-up conveying summer heat, 3-6 seconds high-speed slow-motion bottle opening, 6-9 seconds smooth push-in of drinking the beverage, 9-12 seconds whip pan to the beach, 12-15 seconds freeze-frame ending. The author self-rates the completion at only 50%, due to repeated regeneration from broken character faces and deformed bottles, and the final cut is 20 seconds.

  8. 通义千问 · 图像与音频模型62

    Alibaba releases Qwen-Image-2.1-Turbo accelerated image generation model

    Qwen released Qwen-Image-2.1-Turbo, an accelerated checkpoint of Qwen-Image-2.1 for text-to-image and image editing, requiring only 8 denoising steps.

    Why it matters: 8-step sampling and KV cache reuse of text and reference image context let creators assess the speedup potential of their image generation and editing workflows.

  9. ArchiGen AI · 图像生成与ComfyUI实战50

    ComfyUI 4K tiled upscaling: why seams change building structure

    Although ComfyUI tiled upscaling can make 4K rendering run on limited VRAM, each tile boundary can become a design change, producing misaligned parapets, repeated facade bays, or restarted glass reflections. The recommendation is to use overlapping tiles and low denoise, overlay a grid matching the actual tile spacing, and at 100% view check long lines, repeated bays, reflections, and vegetation at cross-boundary areas along the grid lines. If a seam changes the building structure, rerun that region locally with sufficient context rather than masking it with sharpening.

  10. Recraft 官方博客36

    Turning a Supporting Character into a Vector Mascot with Recraft V4.1 Vector

    Recraft's official blog published a tutorial on how to turn a supporting character into a vector mascot with Recraft V4.1 Vector (Create → Model, 4 credits per image) and generate emoji packs and sticker packs. The process includes simplifying shapes, generating a sticker emoji sheet with six poses at once in 16:9, exporting SVG for lossless scaling, and testing readability at 16 to 32 pixels.

  11. VideoGen · 视频剪辑与镜头实战22

    What Makes a Truly Good AI Image Generator? VideoGen Offers Seven Evaluation Criteria

    VideoGen proposes seven dimensions for evaluating AI image generators: prompt adherence, text rendering, reference image and style control, speed, set consistency, licensing clarity, and whether images can be turned directly into video. In VideoGen, GPT Image 2.5 Flare handles fine detail and readable text, Nano Banana is another main quality option, and Flux Schnell delivers images in seconds with 1 to 4 denoising steps, limited to the Low tier; each edit supports up to 5 reference images.

  12. Recraft 官方博客48

    How to Make a Four-Panel Comic with Recraft for Your Own Character

    Recraft's official blog published a tutorial on how to make a four-panel comic with an original character in Recraft Studio: first generate a 2:1 four-panel storyboard sketch with V4.1 Flash (0.5 credits per image), then render each panel with Nano Banana 2.1 (7 credits per image), attaching character and environment reference images to maintain consistency. Text bubbles are best added with the text tool rather than an image model, and the result can be exported as a social media carousel, a vertical long image, or a webcomic page.

  13. ComfyUI Wiki · 工作流与开源创作分享62

    HEISS UI Releases v0.17.0: Adding a Prompt and Gallery Frontend to ComfyUI

    HEISS UI is a local frontend for ComfyUI that puts a prompt box and gallery in front of existing models, while ComfyUI still executes tasks underneath. It supports 28 model families out of the box and includes vendor-recommended samplers, schedulers, steps, and guidance values; download buttons are provided for missing text encoders, VAEs, and node packs, and custom ComfyUI workflows can be imported as controls in API format or as regular files.

  14. ArchiGen AI · 图像生成与ComfyUI实战22

    AI Makes Images Cheap and Judgment Expensive: The Focus of Architectural Visualization Is Shifting

    AI is shifting the value of architectural visualization from "generating the first image" to "guiding iteration, identifying design errors, and documenting what an image can support." As image generation gets faster, the bottleneck moves to selection, correction, and evidence: a seemingly perfect render may quietly alter floor plans, doors and windows, or reflections, so direction, source control, defect detection, evidence control, and stopping rules are needed. The article argues that prompting is only a thin layer of the work, craft knowledge will become diagnostic knowledge, and skipping the fundamentals will create a "review deficit."