Skip to content
Date and source

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

Mar 29Fri
Mar 25Mon
Feb 27Tue
Feb 26Mon
  1. Hugging Face Blog22

    Hugging Face Details AI Watermarking Tools and Techniques: From Nightshade and Fawkes to Truepic

    Hugging Face publishes an article surveying watermarking approaches for AI-generated content, distinguishing between two pathways: embedding at generation time and adding after generation. It also introduces watermarking and detection tools available on the Hub. The article mentions image "invisible modification" tools such as Glaze and Photoguard, as well as data poisoning tools like Nightshade and Fawkes, used to prevent models from learning or generating faces. Truepic embeds metadata according to the C2PA standard and combines it with watermarks to enhance provenance verifiability.

Feb 19Mon
Feb 15Thu
  1. OpenAI News82

    OpenAI Research: Video Generation Models as World Simulators

    OpenAI explores large-scale training of generative models on video data, jointly training text-conditioned diffusion models on videos and images of varying durations, resolutions, and aspect ratios, using a transformer architecture that operates on spatiotemporal patches of video and image latent codes. Its largest model, Sora, can generate one-minute high-fidelity videos. Results indicate that scaling video generation models is a promising path toward building general-purpose physical world simulators.

    Why it matters: OpenAI publicly reveals Sora's technical roadmap for the first time, explaining how video generation models can be scaled into physical world simulators.

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.

Jan 15Mon
Jan 14Sun
Jan 4Thu
Jan 2Tue
  1. Hugging Face Blog62

    Hugging Face Releases Advanced Training Script for SDXL Dreambooth LoRA

    Hugging Face releases an advanced training script for SDXL Dreambooth LoRA, integrating Pivotal Tuning and the Prodigy optimizer into diffusers, along with reusable training parameters.

    Why it matters: Hugging Face officially integrates Pivotal Tuning and the Prodigy optimizer into diffusers training scripts, providing directly reusable parameters and experimental comparisons.

Dec 5Tue
Nov 9Thu
  1. Hugging Face Blog78

    Using Latent Consistency LoRA to Generate SDXL Images in 4 Steps

    Hugging Face releases the LCM LoRA method, which trains a small number of LoRA adapter layers instead of distilling the entire model, reducing image generation for SDXL and Stable Diffusion from 25 to 50 steps down to 4 to 8 steps.

    Why it matters: LCM LoRA enables SDXL to generate images in 4 steps. The article provides directly runnable diffusers code and speed comparisons across multiple hardware configurations.

Nov 6Mon
Oct 24Tue
Oct 19Thu
  1. OpenAI News62

    DALL·E 3 Launches on ChatGPT Plus and Enterprise

    OpenAI announced that DALL·E 3 is now available in ChatGPT Plus and Enterprise. To prepare for a broader release, OpenAI developed a set of safety mitigations and also shared its progress on content provenance research.

    Why it matters: DALL·E 3 is open to ChatGPT Plus and Enterprise, and the official announcement also explains the safety mitigations made for the expanded release.

Oct 3Tue
  1. Hugging Face Blog32

    Hugging Face Diffusers supports accelerated Stable Diffusion XL inference with JAX on Cloud TPU v5e

    Hugging Face Diffusers now supports running SDXL inference on Cloud TPU v5e via JAX, achieving high-performance, low-cost deployment with JIT compilation and XLA parallelism. The demo generates 4 images of 1024×1024 in parallel on multiple TPU v5e-4 instances in about 4 seconds, with pure generation time of about 2.3 seconds; TPU v5e costs less than half of TPU v4.

Oct 2Mon
Sep 29Fri
Sep 18Mon
  1. Hugging Face Blog30

    Getting started with 3D Gaussian Splatting: principles and prospects of real-time radiance field rendering

    3D Gaussian Splatting is a rasterization technique that can learn from a small number of images and render photorealistic scenes in real time. It first uses COLMAP for Structure from Motion to estimate a point cloud, then converts each point into a Gaussian and trains it, achieving fast rendering through differentiable Gaussian rasterization. The costs are high VRAM usage (4GB for viewing, 12GB for training) and large scene files (1GB+), and it is not yet compatible with existing rendering pipelines such as Vulkan, DirectX, and WebGPU.

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 30Wed
Aug 16Wed
Aug 9Wed
  1. Hugging Face Blog22

    How to optimize the Bark text-to-speech model with 🤗 Transformers

    Based on 🤗 Transformers, Optimum, and Accelerate, three optimizations can reduce the VRAM usage of the Bark text-to-speech model and speed up inference. Bark was proposed by Suno AI, has been supported since Transformers v4.31.0, consists of four models—semantic, coarse acoustics, fine acoustics, and EnCodec decoding—and offers small and large checkpoints.

  2. 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.

Aug 4Fri
Aug 1Tue
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.

Jul 21Fri
Jul 20Thu
  1. Hugging Face Blog22

    One year of the Hugging Face Diffusers library: a look back at progress in text-to-image, video, and 3D models

    Hugging Face's Diffusers library has reached its one-year anniversary, having expanded from text-to-image to video, 3D, and image editing. The library has added support for models such as DeepFloyd IF, SDXL, VideoFusion, Text2Video-Zero, and OpenAI Shap-E, and integrates LoRA, Torch 2.0 optimizations, and safety checking components.

Jul 17Mon
  1. Hugging Face Blog60

    Hugging Face builds an AI WebTV video stream with Zeroscope and MusicGen

    Hugging Face released an experimental AI WebTV demo that uses the open-source text-to-video model Zeroscope and the music generation model MusicGen to automatically generate and stream short videos.

    Why it matters: It breaks down the complete pipeline for building an automatically generated video stream with Zeroscope, MusicGen, and FILM, and includes failure cases and prompt suggestions.

Jul 14Fri
Jun 26Mon
  1. Hugging Face Blog22

    Hugging Face Newsletter Issue 4: Bias in text-to-image models

    Hugging Face released Issue 4 of its "Ethical and Social Newsletter," focusing on bias in text-to-image models. The article outlines five sources of bias: training data, pretraining data filtering, CLIP inference, the model's latent space, and post-hoc filtering, and points out that Stable Diffusion v2.1 and ERNIE ViLG produce culturally stereotyped results under the same prompt, "a house in Beijing." The team also introduced the Stable Bias project, a tool for exploring and comparing bias in generated images.

Jun 15Thu
May 25Thu
  1. Hugging Face Blog22

    Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum

    Using quantization-aware training (QAT) with OpenVINO NNCF combined with Token Merging, Stable Diffusion achieves a 5.1x inference speedup and a 4x reduction in model size on Intel CPUs. The optimization starts from a model fine-tuned on the Pokemons dataset, requires only 4096 iterations, completes within one day on a single GPU with 24GB of VRAM, and has been integrated into the Diffusers training scripts.

May 23Tue
May 8Mon
  1. Hugging Face Blog30

    A deep dive into text-to-video models: development and challenges from GANs to diffusion models

    A Hugging Face blog post traces the development of text-to-video models: early GAN- and VAE-based methods were limited by low resolution and short duration, after which Phenaki, Make-A-Video, NUWA, VideoGPT, CogVideo, and others shifted to transformer architectures, while current mainstream approaches use diffusion models. Text-to-video must ensure spatiotemporal consistency across frames and faces three major challenges: high compute costs, scarce high-quality datasets, and vague video descriptions; models can typically generate only very short clips.

Apr 26Wed
Mar 28Tue