Efficient Controllable Generation for SDXL with T2I-Adapters
Hugging Face published a blog post detailing T2I-Adapters for Stable Diffusion XL (SDXL), a lightweight conditioning mechanism that enables controllable image generation without full fine-tuning. The approach allows users to guide SDXL outputs using structural signals such as depth maps, edge detection, and pose estimation. T2I-Adapters offer a parameter-efficient alternative to ControlNet for the SDXL architecture, with integration into the Diffusers library.
Related guides (3)
Related events (8)
Exploring Simple Optimizations for SDXL
This Hugging Face blog post explores practical optimization techniques for Stable Diffusion XL (SDXL) inference. It covers methods to improve throughput and reduce memory usage when running SDXL, targeting practitioners deploying the model. The content is oriented toward applied inference efficiency rather than novel research.
Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e
Hugging Face published a technical blog post detailing how to accelerate Stable Diffusion XL inference using JAX on Google Cloud TPU v5e hardware. The post covers the integration of JAX-based diffusion pipelines with TPU v5e, demonstrating performance gains from hardware-software co-optimization. This represents a practical deployment pattern for large image generation models on non-GPU accelerators.
Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive
This Hugging Face blog post details how to accelerate Stable Diffusion Turbo and SDXL Turbo inference using ONNX Runtime and Microsoft's Olive optimization toolkit. The post covers the workflow for converting and optimizing diffusion models for faster deployment. This is a practical inference optimization guide targeting practitioners deploying image generation models.
SDXL in 4 Steps with Latent Consistency LoRAs
Hugging Face demonstrates combining Latent Consistency Models (LCMs) with LoRA adapters to enable high-quality image generation with Stable Diffusion XL in as few as 4 inference steps. This approach dramatically reduces the number of diffusion steps required compared to standard SDXL, lowering inference latency and compute cost. The technique leverages consistency distillation applied via lightweight LoRA weights, making it accessible without full model retraining.
Train your ControlNet with diffusers
This Hugging Face blog post provides a technical guide for training ControlNet models using the diffusers library. It covers the process of conditioning diffusion models on additional inputs such as edge maps, depth maps, or other spatial signals to enable fine-grained image generation control. The post targets practitioners looking to implement custom ControlNet pipelines on their own datasets.
Stable Diffusion XL on Mac with Advanced Core ML Quantization
Hugging Face details the process of running Stable Diffusion XL (SDXL) on Apple Silicon Macs using Core ML with advanced quantization techniques. The post covers how quantization reduces model size and memory requirements to make SDXL feasible on consumer Mac hardware. This represents a practical deployment advance for running large diffusion models at the edge on Apple devices.
ControlNet in 🧨 Diffusers
Hugging Face's Diffusers library added support for ControlNet, a technique that enables fine-grained spatial and structural control over diffusion model image generation. The blog post covers how ControlNet conditions image synthesis on auxiliary inputs such as edge maps, depth maps, pose skeletons, and segmentation masks. This integration makes ControlNet-based generation accessible through the standard Diffusers pipeline API.
Diffusers welcomes Stable Diffusion 3.5 Large
Hugging Face's Diffusers library has added support for Stable Diffusion 3.5 Large, Stability AI's latest image generation model. The blog post covers integration details, usage patterns, and how to run the model within the Diffusers ecosystem. This represents a standard tooling integration announcement for a recently released frontier image generation model.