Skip to content
Date and source

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

Sep 19Sat
  1. Wireflow · AI短剧与视频制作教程22

    Best product video generators of 2026: a review of eight tools including Wireflow, Creatify and PixVerse

    The 2026 product video generator review ranks eight tools on four criteria: product fidelity, reusability, shot control and output aspect ratio. Wireflow ranks first, linking product images, video models and an editor on a node canvas so the same workflow can be reused in bulk across hundreds of SKUs; Creatify generates AI presenter ads directly from a product link, PixVerse excels at camera movement in image-to-video, and HeyGen is known for lip-sync and multiple languages.

  2. 宝玉的分享 · 创作与项目分享62

    Baoyu uses GPT 6 Astra and Codex to create a 3D version of "The Peach Blossom Spring" and publishes the prompts

    Baoyu used GPT 6 Astra in ChatGPT Pro to generate a 3D web version of "The Peach Blossom Spring," splitting the full text into 20 scenes and supporting following the text into the scene, slow chapter-by-chapter reading, and switching between the original and vernacular text. He replaced the system TTS with real-person recitation by CCTV's Li Lihong, used SRT timestamps to sync chapter transitions and sentence highlighting, then had Codex split the Base64-embedded MP3 into separate files and replace the stream-and-bird ambience, shrinking the HTML from 5.6 MB to about 777 KB.

  3. ArchiGen AI · 图像生成与ComfyUI实战38

    A two-input controlled test in ComfyUI using line art and clay passes from a locked camera

    The tutorial proposes exporting two passes, line art and clay/simple material, from the same locked camera in ComfyUI, and using a ControlNet two-condition controlled test to see which input protects which architectural facts. The method fixes the checkpoint, VAE, sampler, seed and resolution, changing only the conditioning path, and runs four cases: clay alone, line art alone, equal-weight pairing and tuned pairing, with four seeds per case.

  4. Wireflow · AI短剧与视频制作教程22

    Best batch image generation tools of 2026: a comparison of 8 including Wireflow, OpenArt and Recraft

    2026 batch image generation tools fall into three categories: batch prompt apps, template renderers and API platforms. Wireflow, rated best overall, links multiple image models on a node canvas and runs batch jobs through a single REST endpoint; OpenArt supports CSV/TXT batch generation of up to 500 images, the highest free batch limit; Recraft offers an asynchronous batch API at about $0.035 for raster images and about $0.08 for vector images.

Sep 18Fri
  1. Oimi · 中文图像视频教程62

    10 Popular Portrait Poster Prompts (2026)

    This tutorial compiles 10 portrait poster prompts, covering styles such as Japanese ink-wash minimalism, Y2K collage, silhouette narrative, underground club, cinematic red-and-blue color scheme, and typographic outlines; each comes with a complete English prompt and adjustment tips. The author suggests pasting the prompts into ChatGPT or Gemini and replacing the bracketed placeholders; if you need to preserve your own face, you can add an identity instruction at the beginning and attach a clear frontal photo. Use ChatGPT for long, structured text prompts, and Gemini for scenarios with high facial-similarity requirements.

  2. ArchiGen AI · 图像生成与ComfyUI实战20

    AI Render Collaboration Canvas Review: Can Teams Track a Single Image's Revisions, Reviews, Approvals, and Archiving?

    AI rendering products are starting to emphasize shared canvases and team collaboration, but the evaluation focus should be the decision path rather than whether collaboration buttons exist. The article suggests trialing with five states—draft, shortlisted, checked, approved, and superseded—and testing unauthorized operations, permission revocation, and attribution records. Generation is not checking, comments are not approval, and downloading is not archiving; if a product cannot provide both creation history and approval history, teams need to separately decide where to store streamlined approval records.

  3. ArchiGen AI · 图像生成与ComfyUI实战22

    An Approved ComfyUI Render Is More Than a PNG: How to Preserve Workflows, Inputs, Environment, Checks, and Usage Decisions

    After a ComfyUI render is approved, the project record should include five types of files: the selected output, an explicit workflow JSON, an input manifest, an environment snapshot, and a review/usage record. The official example states that workflow information can be embedded in image metadata and dragged back into ComfyUI for restoration, but exporting, optimizing, or document processing may alter the file, so a file hash must be computed at approval time and written into the decision record.

  4. VibeClips · AI视频创作教程22

    VIBE Tutorial: How to Create AI Digital Human Talking-Head Videos with Talking Avatar

    VIBE's Talking Avatar model requires only a frontal photo and a voice recording to generate a 480p or 720p lip-synced digital human talking-head video, with no text prompt needed, and the output language follows the recording. The model is billed per use: 35 tokens for 480p and 60 tokens for 720p, regardless of recording length, and the output aspect ratio is locked to that of the uploaded photo.

  5. WellSaid · 官方博客22

    How to Localize Marketing Campaigns with AI Voice

    WellSaid's official blog published a guide on how to localize marketing campaigns with AI voice. The process includes preparing localized scripts, selecting voices with regional accents and dialects for each market, generating and previewing voiceovers, adjusting pronunciation and pacing, and then reusing the same creative direction across markets. AI voice lets teams avoid rescheduling recording sessions for every script change, shifting time and budget from coordinating recordings to comparing and polishing versions.

  6. 优设 · 创作者专栏34

    How to make AI posters look high-end? 4 pitfalls to avoid to escape a cheap tech feel

    AI posters look cheap mostly because of four basic problems: style words that are too vague, a messy information hierarchy, too many decorative elements, and unclear prompts. The article breaks down these common issues and offers fixes: control the amount of information, establish clear primary and secondary elements, make "high-end feel" concrete, and write poster prompts in order.

Sep 17Thu
  1. Creator Animation · AI影片制作教程12

    How independent creators can sell AI films online in the first 90 days: a practical guide

    Creator Animation released a practical guide for independent creators selling AI films online in the first 90 days, splitting the release cycle into three phases: packaging and distribution infrastructure, promotion that connects directly with audiences, and retention and scaling. The platform offers the first 10GB of storage free, $0.40/GB beyond that, creators keep an 80% revenue share, viewers can watch without registering, and they can use a $9/month Download Pass or buy offline versions individually.

  2. Creator Animation · AI影片制作教程18

    A guide to building an AI filmmaking tool stack for content monetization

    Creator Animation offers an on-site AI Film Studio where creators can use prepaid credits to directly generate multi-scene films and keep 80% of their work's revenue under an 80/20 split. The platform has no ad interruptions or algorithmic review thresholds, viewers can watch for free, fans can buy a $9/month Download Pass for offline saving, and creators start with 10GB of free storage.

  3. note · howrass_note · 图像视频创作分享40

    A practice log of making a 5-minute, 2K music video with lyrics using MiniMax H3

    A video-making novice used the locally runnable MiniMax H3 video generation model, together with Google Colab cloud GPUs, to complete a music video for the SUNO original song "ヘッドホンの息": about 5 minutes 16 seconds long, 1440p (QHD), with lyrics throughout. The production ultimately used 44 storyboard images, generated more than 200 images in total, and had about 250 failed videos; the author says technical details will be covered in a separate article.

  4. ArchiGen AI · 图像生成与ComfyUI实战28

    A reusable ComfyUI workflow should withstand four different types of architectural input

    A ComfyUI workflow that can generate a single architectural rendering may just be tuned to one screenshot; ArchiGen suggests testing portability with four clearly different inputs: a clean clay look, a glass-curtain-wall interior, a low-contrast dusk view, and a cluttered urban environment, which respectively expose problems such as fabricated facade details, depth errors, fake openings, and noise leaking into structural control.

  5. VibeClips · AI视频创作教程22

    VIBE free AI video generator hands-on: what the 2026 free version can do

    VIBE's free version offers four models: Seedance Pro Fast, LTX 2 Distilled, PRUNA V and LTX 2.5 Fast, supporting text-to-video and image-to-video, with no credit card required and no trial period. Free models max out at 720p (Seedance Pro Fast is 480p), every export carries a watermark, and only PRUNA V supports audio and photo lip-sync digital human mode.

  6. ArchiGen AI · 图像生成与ComfyUI实战22

    Don't judge an AI renderer by the first image alone: ArchGen proposes an exit test for revisions, archiving and handover

    ArchGen AI proposes that procurement testing for AI renderers should not stop at image quality, speed, price and integration, but extend to revisions, handover and archiving after the first image. Its five-part exit package requires traceable sources, generation recipes, result specifications, review records and limited revision capability, and has a second operator make one small change using only the package, recording the time taken and the scope of the change's impact. The archiving test has a third person reopen the package after the project has cooled down to confirm that delivered images map to source versions, products, engines, dates and settings.

  7. MattVidPro · YouTube 创作视频50

    YuE2 local AI music model hands-on: comparison with Suno V6 and Pinokio installation tutorial

    YuE2 is the best-performing locally run AI music model to date; the video compares it with Suno V6 on songs and demonstrates exaggerated prompts and parameter adjustments. YuE2's code is under the Apache 2.0 license and its model weights are CC BY-NC 4.0; individual creators can commercialize outputs, while enterprise commercial use requires a separate license. At 17:41 there is a tutorial for installing it locally on a PC via Pinokio and Wan2GP.

Sep 16Wed
  1. note · lpp · 图像视频创作分享38

    Running YuE2 AI music generation on an RX9070XT: ROCm installation tutorial plus a bonus GUI

    Installing the YuE2-3B AI music generation model via ROCm on a Windows PC with an RX9070XT; the author published the installation steps and bonus Gradio GUI code. Switching to ROCm10.x greatly improved generation speed, while ROCm7.x requires applying a pull request on GitHub to fix a Flash Attention error. A cover-integrated GUI version was also released in the fourth week of September.

  2. Promptsref.com · 创作分享22

    3 illustration SREF codes to make Midjourney works feel more hand-drawn

    Promptsref.com shares 3 Midjourney illustration SREF codes, respectively featuring sparse, imperfect line art; rough, doodled geometric shapes; and a gothic dark style blending Japanese manga with retro posters. All three build a hand-drawn feel with black lines, warm paper tones, and a small amount of accent color, suitable for children's books, indie comics, posters, stickers, and game key art. Two of them are member-exclusive SREFs.

Sep 15Tue
  1. 张小闲 · 创作者专栏62

    Generate poster title art text with a single prompt, covering styles such as brush calligraphy, jelly letters, and neon.

    The author put together a playbook for generating poster title art text with a single prompt, writing the theme, font feel, color, and atmosphere into the prompt to get a first version out in just over ten seconds. The author tried directions including handwritten brush calligraphy, pink-orange jelly letters, purple flowing light, tech speed letters, futuristic neon, and premium gold lettering, covering scenarios such as e-commerce posters, event key visuals, product detail pages, and AI design covers; the prompt structure is not complicated, and it can be reused by swapping out the theme and style descriptions.

Sep 14Mon
  1. Cartesia 官方博客22

    TTS models and voices are not the same thing: Cartesia breaks down fixed-speaker, multi-speaker, and voice cloning

    Cartesia's official blog points out that a TTS model and the voice it uses are two separate concepts, with the voice being more like an input than the model itself. Fixed-speaker models receive only text, multi-speaker models can additionally select preset voices, and zero-shot cloning models accept 10 to 60 seconds of reference audio as a prompt; Cartesia's Sonic end-to-end model supports Instant Voice Cloning. Professional voice cloning (PVC) requires fine-tuning the model with a larger recording dataset and can take hours.

Sep 10Thu
Sep 3Thu
Aug 25Tue
  1. Hugging Face Blog62

    Gradio launches gr.Workflow: turning AI pipelines into a drag-and-drop canvas with auto-generated APIs

    Gradio's built-in gr.Workflow describes AI pipelines as graphs of typed nodes, offering a drag-and-drop canvas where each node can run and intermediate results are visible; the same graph is also a REST API and can be deployed to Hugging Face Spaces with one click.

    Why it matters: Gradio turns multi-step AI pipelines into a visual graph and automatically exposes REST interfaces, giving teams a basis to assess migration costs against their existing production workflows.

Jul 23Thu
  1. Hugging Face Blog62

    Diffusers natively supports Nunchaku 4-bit diffusion inference

    A Hugging Face blog post explains that Diffusers now natively supports Nunchaku's 4-bit diffusion inference; loading a quantized checkpoint only requires calling from_pretrained(), with no local CUDA compilation needed.

    Why it matters: Nunchaku's 4-bit quantized inference is now natively integrated into Diffusers, allowing creators to evaluate the trade-off between VRAM usage and speed for image generation on consumer-grade GPUs.

Jul 6Mon
  1. Hugging Face Blog22

    PRX Part 4: Our Data Strategy

    The fourth installment of the PRX series reveals its data pipeline: pre-training data is composed of a mix of public and internal datasets, with VLMs used to regenerate long image descriptions, which are then converted into corpora suitable for streaming training. The team switched to the Qwen3-VL text encoder and computes text latents in real time during training, with measured throughput loss of approximately 3–4% (roughly one extra day for a 30-day training run). Images are uniformly encoded at JPEG quality 92, and initial re-encoding is nearly imperceptible in practice.

Jun 9Tue
Feb 3Tue
  1. Hugging Face Blog22

    PRX Text-to-Image Model Training Design: Lessons from Ablation Studies

    The Hugging Face blog publishes the second installment of the PRX text-to-image model training series, using ablation studies to document which training techniques actually work. The baseline is PRX-1.2B with 1.2B parameters, using pure Flow Matching, Flux VAE latent space, 256×256 resolution, a global batch size of 256, and 100k training steps, with data consisting of 1 million synthetic images generated by MidJourneyV6.

Sep 2Tue
Aug 19Tue
Jul 31Thu
  1. Hugging Face Blog30

    Implementing an MCP Server in Python: A Gradio-Based AI Shopping Assistant

    A Hugging Face blog post demonstrates how to build an AI shopping assistant in Python using Gradio's MCP integration, automatically converting Python functions into MCP tools callable by an LLM. The example calls the IDM-VTON virtual try-on model via the Gradio API, combined with VS Code AI Chat and the playwright MCP server to browse web pages, enabling clothing search and try-on effect generation.