Skip to content
Date and source

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

Oct 23Fri
  1. pyvideotrans 官方发布65

    pyvideotrans v4.17 released

    pyvideotrans v4.17 released, adding the Audio.cpp speech recognition channel, and adding noise reduction and vocal separation models based on audio.cpp. It also fixes the nemotronasr repeated download issue, adds the Opper translation channel, and adds a 'further simplify' option to subtitle translation.

    Why it matters: The new version adds the Audio.cpp speech recognition channel and noise reduction models, and optimizes the subtitle translation simplification option, suitable for evaluating upgrades to the video translation and dubbing workflow.

Oct 19Mon
  1. InvokeAI 官方发布36

    InvokeAI 7.0.0 alpha 3 released: adds board sharing and Qwen-Image-2.1 support

    InvokeAI 7.0.0 alpha 3 has been released, adding role-based board sharing, support for the Qwen-Image-2.1 image model, and the SageAttention acceleration backend for NVIDIA GPUs. This version speeds up full-image generation at 2048² resolution on an RTX 4090 by 15–35% and video generation by 12–35%. Note that v7 performs a one-way upgrade of the v6 database, and the official recommendation is to install and test with a brand-new root directory.

  2. LichtFeld-Studio 官方发布22

    LichtFeld Studio 0.5.4.1 released: bug-fix patch plus drag-and-drop export, training resume, and more

    LichtFeld Studio 0.5.4.1 is released, supporting dragging splats from the scene graph into folders or directly into Blender as PLY/SPZ, with the up axis selectable in preferences. This version adds training session resume, batch video frame extraction at the source frame rate, and numeric position, rotation, and scale fields for crop boxes and ellipsoids. It also fixes image loading when no GPU JPEG decoder is available, Python console freezes, and VRAM exhaustion when merging large compositions.

Oct 15Thu
  1. Black Forest Labs 官方博客82

    Black Forest Labs releases FLUX 3 Image Klein open-weight model

    Black Forest Labs releases FLUX 3 Image Klein, a 5.6B-parameter open-weight model that supports text-to-image, image editing, and multi-reference generation with up to 10 reference images, and features native 4K generation, pixel-level editing, and bounding-box control.

    Why it matters: An Open-Source Image Model with 5.6B Parameters Brings 4K Generation and Pixel-Level Editing Down to 8GB VRAM, Allowing Evaluation of Local Image Generation and Editing Solutions.

Oct 13Tue
  1. pyvideotrans 官方发布40

    pyvideotrans v4.16 Released: Fixes Edge-TTS 403, Adds audio.cpp and fish.audio Dubbing Channels

    pyvideotrans released v4.16, fixing the Edge-TTS 403 issue and adding two new dubbing channels: audio.cpp and fish.audio API. This version also adds the Atlas Cloud translation channel, a French WebUI interface, and includes "use LLM to re-segment sentences instead of LLM error correction" in the advanced options for subtitle translation.

Oct 9Fri
  1. Hugging Face Blog46

    Building six small models on Hugging Face with ML Intern: from a 0.8B prompt rewriter to a camera-angle LoRA

    Because the official Qwen-Image 2.1 prompt rewriter is a 9B model requiring about 20 GB of memory, the author used ML Intern in HuggingChat to build a 0.8B version that runs on CPU, achieves a 99.7% valid output rate, and consumes about one quarter of the teacher model's tokens, with a total compute cost of $16 including 8,797 annotations.

Oct 7Wed
  1. pyvideotrans 官方发布38

    pyvideotrans v4.15 released: Deepgram and ElevenLabs channels updated, silence removal adjustment added

    pyvideotrans released a v4.15 Windows pre-packaged build; MacOS/Linux require source deployment. The new version updates the Deepgram.com channel models and adds speech synthesis support, updates the Elevenlabs.io models and removes models that will be deprecated, and adds subtitle dubbing silence buffer removal and intensity adjustment in the advanced options. It also adds the Audexum speech recognition channel, the Infistar translation channel, and Azerbaijani language support.

Sep 30Wed
  1. facefusion 官方发布20

    facefusion 3.9.1 released

    facefusion released version 3.9.1, updating to the latest onnxruntime version and limiting the arena workaround to affected onnxruntime versions. This version also fixes a performance issue with the content analyzer under CoreML.

Sep 26Sat
  1. pyvideotrans 官方发布38

    pyvideotrans v4.14 Windows pre-packaged version released

    pyvideotrans releases v4.14 Windows pre-packaged version; the full package is 2.7G, and the 360MB patch package is only for overwriting the old package. This version optimizes speech, subtitle and image alignment algorithms, checks before Google Translate and automatically switches to Microsoft Translator when blocked by 429, and optimizes openai-whisper model downloads. MacOS/Linux require source deployment; if the new version has issues, users can continue using v4.13/v4.03.

Sep 21Mon
  1. pyvideotrans 官方发布38

    pyvideotrans v4.13 Released: Optimized Model Download Retry and Whisper Sentence Segmentation, Added Doubao TTS 2.0 Voiceover Characters

    pyvideotrans v4.13 released a Windows pre-packaged version with automatic retry after model download failures and an optimized re-segmentation algorithm for Whisper model recognition. This version improves speech recognition, subtitle translation, and speech synthesis model support for SiliconFlow, Minimax, and OpenRouter, adds Doubao TTS 2.0 voiceover characters, and restructures the settings window and menu architecture. Local voiceover channels such as Qwen-TTS and Higgs have dropped 8-bit quantization, and the media merge function now includes a pause button.

Jan 29Thu
  1. Hugging Face Blog40

    Gradio Team Launches Daggr: Chaining AI Workflows with Python Code and Auto-Generating Visual Canvases

    The Gradio team open-sources Daggr, a Python library that lets you chain Gradio apps, ML models, and custom functions with code and auto-generate visual canvases. It supports inspecting any node's output, re-running individual steps, configuring fallback nodes, and automatically saving workflow state and cached results. Daggr requires Python 3.10 or later, can be installed via pip, and workflows can be deployed to Hugging Face Spaces for sharing.

Jan 6Tue
Apr 9Wed
  1. Hugging Face Blog40

    Hugging Face and Cloudflare Partner to Enable Real-Time Voice and Video with FastRTC

    Hugging Face and Cloudflare have reached a partnership. FastRTC developers can access Cloudflare's TURN network, which spans over 335 locations worldwide, using a Hugging Face Token. They can stream 10GB of data per month for free with no credit card required. This integration will be available in FastRTC version 0.0.20 and above, and users can switch to a Cloudflare account to expand beyond the limit.

Jan 27Mon
  1. Hugging Face Blog60

    The Diffusers Team Surveys the State of Open-Source Video Generation Models and Optimization Approaches

    The Hugging Face Diffusers team publishes an article surveying the state of open-source video generation models and introducing how Diffusers supports these models. The article lists open-source models such as CogVideoX, Mochi-1, HunyuanVideo, Allegro, and LTX-Video, noting that high resource requirements, generalization ability, and latency are the main limitations.

    Why it matters: The Diffusers team systematically surveys the state of open-source video models and provides an optimization combination that reduces HunyuanVideo's VRAM usage to approximately 6.5GB.

Dec 9Mon
  1. Hugging Face Blog22

    Hugging Face community releases open preference dataset for text-to-image

    Hugging Face's Data is Better Together community releases an Apache 2.0 licensed text-to-image preference dataset covering multiple image generation categories, mixing different model families and prompts of varying complexity. The dataset is based on images generated by Flux and Stable Diffusion models, with ready-to-use preference datasets and flux-dev-lora-finetune provided. Preprocessing and post-processing code is open-sourced on GitHub.

Sep 23Mon
  1. Hugging Face Blog34

    FineVideo: How the open-source video dataset with 43k videos and 3.4k hours was built

    To address the scarcity of open-source video datasets, the team built FineVideo, which contains 43k videos totaling 3.4k hours, annotated with rich descriptions, narrative details, scene segmentation, and QA pairs. The dataset starts from 1.9M English videos from YouTube-Commons, filtered by word density and visual dynamism, with content annotation and structured output completed using Gemini 1.5 Pro and GPT-4o.

Feb 3Sat
  1. Hugging Face Blog62

    SegMoE Released: Building Mixture-of-Experts Diffusion Models from Scratch

    Segmind releases the SegMoE framework, which can create Mixture-of-Experts (MoE) diffusion models from scratch and has been integrated into Hugging Face diffusers. This release includes three model versions—SegMoE-4x2, SegMoE-2x1, and SegMoE-SD4x2—along with the segmoe code package for building custom MoE models. The models are licensed under Apache 2.0.

    Why it matters: The release provides code for building MoE diffusion models from scratch along with three merged versions, enabling creators to combine multiple pretrained models into new ones.

Sep 29Fri
Sep 13Wed
  1. Hugging Face Blog60

    Hugging Face releases Würstchen: a fast image diffusion model with a highly compressed latent space

    Hugging Face released the Würstchen image generation diffusion model, whose text-conditioning part works in a highly compressed latent space, achieving 42x spatial compression through Stage A's VQGAN and Stage B's Diffusion Autoencoder, with Stage C trained as a Prior in that latent space.

    Why it matters: Würstchen uses 42x spatial compression to cut training cost to about one-sixth of SD1.4, which can be used to evaluate low-VRAM image generation options.

Sep 8Fri
  1. Hugging Face Blog62

    Hugging Face brings T2I-Adapter controllable generation support to SDXL

    The Hugging Face Diffusers team, in collaboration with the T2I-Adapter authors, provides T2I-Adapter support for Stable Diffusion XL and releases checkpoints for conditions such as sketch, canny, lineart, depth, and openpose.

    Why it matters: Comparing ControlNet's parameter count and inference overhead, it presents a T2I-Adapter controllable generation solution on SDXL and reusable training scripts.

Aug 9Wed
  1. Hugging Face Blog22

    Deploying Hugging Face models with BentoML: a DeepFloyd IF hands-on guide

    This tutorial demonstrates how to deploy DeepFloyd IF as a production-grade service using the open-source model serving framework BentoML. DeepFloyd IF is an open-source text-to-image model that works directly in pixel space, consists of a frozen text encoder and three cascaded pixel diffusion modules, can progressively upscale a 64x64 px image to 1024x1024 px, and encodes prompts with T5-XXL-1.1.

Jul 27Thu
  1. Hugging Face Blog62

    Apple and Hugging Face run Stable Diffusion XL on Mac with Core ML mixed-bit quantization

    Apple and Hugging Face have ported the Stable Diffusion XL base model to Core ML, usable on Apple Silicon Macs running the macOS 14 public beta; it currently uses the ORIGINAL attention implementation, and the refiner stage has not yet been ported.

    Why it matters: Apple and Hugging Face jointly present a Core ML mixed-bit quantization solution for SDXL on Mac, with measured latency for various models and compression recipes.

Feb 24Fri
  1. Hugging Face Blog38

    Swift 🧨Diffusers: a fast Stable Diffusion app for Mac

    Hugging Face released 🧨Diffusers for Mac 1.1, a native Mac app based on Core ML that can convert community-contributed text-to-image models such as Stable Diffusion and run them locally, with generation speeds up to 2x faster. The app is fully open source, supports coordinated acceleration across CPU, GPU, and the Neural Engine, and automatically selects the best accelerator.

Dec 1Thu
  1. Hugging Face Blog62

    How to run Stable Diffusion with Core ML on Apple Silicon

    Apple engineers provided conversion scripts and inference code, and Hugging Face has converted the weights of Stable Diffusion v1.4, v1.5, v2 base, and v2.1 base into Core ML versions and published them on the Hugging Face Hub.

    Why it matters: Apple engineers and Hugging Face converted Stable Diffusion weights to Core ML and provided two inference paths, in Python and Swift, for generating images locally on Apple Silicon.

Oct 5Wed
Sep 12Mon
  1. Hugging Face Blog31

    What's New in Diffusers 0.3?

    Diffusers 0.3 adds pipelines such as image-to-image, Textual Inversion, and experimental Inpainting, and supports running Stable Diffusion on M1/M2 Macs via mps. After optimization, Stable Diffusion's memory usage drops to 3.2GB with a 10% speed loss; an experimental ONNX exporter and brand-new documentation are also introduced.

Aug 22Mon
  1. Hugging Face Blog62

    Hugging Face Explains How to Run Stable Diffusion with Diffusers

    Hugging Face releases a tutorial explaining how to run the Stable Diffusion text-to-image model with the Diffusers library and breaking down how it works.

    Why it matters: Hugging Face officially breaks down how Stable Diffusion is invoked in Diffusers and the principles of Latent Diffusion's three components, making the image generation process easier to understand.

Jun 7Tue
  1. Hugging Face Blog20

    Illustrated Diffusion Models: From DDPM to a Step-by-Step PyTorch Implementation

    This Hugging Face blog post takes an in-depth look at denoising diffusion probabilistic models (DDPM), based on the 2020 paper by Ho et al., with a step-by-step PyTorch implementation whose code references Phil Wang's implementation. The article covers both the forward noising and reverse denoising processes; the DDPM authors use T=1000 time steps, encode time steps with sinusoidal positional embeddings, and use Wide ResNet blocks as the core module of the U-Net.