KerasFormers
Summary
KerasFormers is a collection of pretrained models integrated into Keras 3, designed to streamline deep learning model deployment for developers.
Similar Articles
@DanKornas: Stop wiring a different integration every time you test a new pretrained model. Transformers is a model-definition fram…
Transformers is a model-definition framework providing unified APIs and centralized model definitions for running pretrained models across modalities, from checkpoint to inference or training.
krea/Krea-2-Turbo
Krea released Krea 2 Turbo, a 12-billion parameter text-to-image diffusion model, available open-weight on Hugging Face with support for multiple inference libraries.
Krea 2 released on Hugging Face
Krea 2 is a 12-billion parameter text-to-image diffusion model released open-weight on Hugging Face, with Raw (base) and Turbo (post-trained) checkpoints available.
Krea 2 Technical Report (59 minute read)
Krea 2 is a series of foundation models for creative image generation, built with a large-scale data infrastructure and multi-stage training pipeline. It introduces a prompt expander and style-reference system to improve steerability and enable creative exploration.
huggingface/transformers
The Hugging Face Transformers repository, an open-source library providing thousands of pretrained transformer models for natural language processing tasks, with support for PyTorch, TensorFlow, and JAX.