@RisingSayak: We just released a new version of Diffusers! This includes many new image and video pipelines (Ideogram4, MotifVideo, e…
Summary
Diffusers library has been updated with new image and video pipelines including Ideogram4, MotifVideo, and the DiffusionGemma model.
View Cached Full Text
Cached at: 07/06/26, 02:00 AM
We just released a new version of Diffusers!
This includes many new image and video pipelines (Ideogram4, MotifVideo, etc.).
But it also includes the recently popular DiffusionGemma 🤌
Check out the notes for full details. https://t.co/49lDK8Vnnk
Similar Articles
Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines
Hugging Face introduces Modular Diffusers, a new framework for building diffusion pipelines using composable, reusable building blocks instead of monolithic pipeline implementations. The system allows flexible mixing and matching of components for image generation workflows, with integration support for visual workflow tools like Mellon.
@omarsar0: This is awesome! I am spending a lot of time on diffusion LLMs these days, so this is perfect timing. I feel like there…
Google DeepMind released DiffusionGemma, an open experimental model that generates text in blocks rather than word-by-word, enabling self-correction and faster output.
@volokuleshov: Congratulations to Google on open-sourcing Gemma Diffusion! I want to give a shout-out to a group of really talented Co…
Google has open-sourced DiffusionGemma, a novel diffusion-based text generation model that uses block diffusion and efficient encoder-decoder techniques, with contributions from Cornell University researchers.
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
NVIDIA NeMo Automodel integrates with Hugging Face Diffusers to enable scalable distributed fine-tuning of diffusion models for image and video generation, supporting models like FLUX.1-dev, Wan 2.1, and HunyuanVideo.
@_philschmid: Gemma goes diffusion! DiffusionGemma with up to 1000+ tokens per second! - Built on Gemma 4 as a 26B MoE model. - 3.8B …
DiffusionGemma, a 26B MoE model based on Gemma 4, achieves over 1000 tokens per second using diffusion for text generation in 256-token blocks, fitting in 18GB VRAM with quantization, released under Apache 2.0.