Personalized generated images with custom styles or objects — On 22 Aug 2022, Stability.AI announced the public release of Stable Diffusion, a powerful latent text-to-image diffusion model. The model is capable of generating different variants of images given any text or image as input. Please note that the … model is being released under a Creative ML OpenRAIL-M license…

New implementation for startup and shutdown logic By reading this piece, you will learn to implement lifespan events in your FastAPI for startup and shutdown logic. From version 0.93.0 onward, the fastapi module officially supports the lifespan event, which replaces the startup and shutdown events. startup and shutdown events will…

Better control for text-to-image generation This tutorial covers a step-by-step guide on text-to-image generation with ControlNet conditioning using the HuggingFace’s diffusers package. ControlNet is a neural network structure to control diffusion models by adding extra conditions. It provides a way to augment Stable Diffusion with conditional inputs such as scribbles…

Based on the HuggingFace’s datasets package The topic for today is about how to speed up the data loading process using the HuggingFace’s datasets package. For your information, the datasets module is part of the HuggingFace’s data loader ecosystem. It serves as an easy-to-use and efficient data manipulation tools. …

Fusing diffusion path for panorama image generation By reading this piece, you will learn to use MutliDiffusion for panorama image generation. Based on the official documentation, MultiDiffusion is … a unified framework that enables versatile and controllable image generation. MultiDiffusion can be readily applied to any a pre-trained text-to-image diffusion…

Upscale generated images by 2x natively The topic for today is about a latent diffusion-based upscaler model to upscale Stable Diffusion generated images by 2x natively. The model was trained by Katherine Crowson in collaboration with Stability AI. As of version 0.13.0, the diffusers package officially supports the stabilityai/sd-x2-latent-upscaler model…

Personalized generated images with custom datasets Previously, I have covered the following articles on fine-tuning the Stable Diffusion model to generate personalized images: How to Fine-tune Stable Diffusion using Textual Inversion How to Fine-tune Stable Diffusion using Dreambooth The Beginner’s Guide to Unconditional Image Generation Using Diffusers By default, doing…

Faster inference and lower memory consumption — The topic for today is on the tips and tricks to optimize diffusers’ StableDiffusion pipeline for faster inference and lower memory consumption. The experiment will be based on the following constants: Module/Framework — Diffuser’s StableDiffusionPipeline Model — runwayml/stable-diffusion-v1–5 Operating System — Ubuntu 18.04.6 LTS Python version — 3.9.16

Efficient and prompt-free framework to get high accuracy with little labeled data — The topic for today is on fine-tuning a text classification model with SetFit framework. Based on the official documentation, SetFit is a … an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers. Based on the Customer Reviews sentiment datasets benchmark, SetFit is competitive and achieve comparable performance with…