Have you used Stable Diffusion and ComfyUI? Do you want to go the next step and step up to consistently producing professional results? If so, then this course is for you.
Have you used Stable Diffusion and ComfyUI? Do you want to go the next step and step up to consistently producing professional results? If so, then this course is for you.
This course is designed for professionals who already have some experience with text-to-image synthesis and want to take their skills to the next level. You will learn how to master Stable Diffusion, the state-of-the-art latent text-to-image diffusion model that can generate photo-realistic images given any text input. You will also learn how to master SDXL, the latest and most advanced version of Stable Diffusion, which can handle challenging concepts and produce images of high quality in virtually any art style. And you will learn how to master ComfyUI, the robust and modular Stable Diffusion GUI and backend that enables you to design and execute advanced Stable Diffusion pipelines using a graph and nodes-based interface.
System Requirements
A windows PC with a powerful GPU capable of running Stable Diffusion. This is NOT a beginner course and students with entry level hardware will struggle to make use of the resources and exercises. At the very least 8GB of VRAM is recommended for the GPU, more is highly advisable.
By taking this course, you will also be able to fine-tune the parameters and the workflows to your needs and preferences, as well as write creative and high-quality prompts that can produce amazing results. You will also gain a deeper understanding of the underlying principles and techniques of text-to-image synthesis, latent diffusion models, and image refinement techniques.
This course is not for beginners who need introductory learning. This course is for professionals who want to master Stable Diffusion, SDXL and ComfyUI and achieve polished, professional outcomes. If you are ready to take your text-to-image synthesis skills to the next level, then enroll in this course today.
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. It is based on the idea of reversing the diffusion process, which gradually transforms an image into random noise. By applying the reverse steps with a neural network conditioned on text, Stable Diffusion can recover the original image from the noise.
SDXL is the latest and most advanced version of Stable Diffusion, which leverages a larger and more powerful UNet backbone with more attention blocks and a larger cross-attention context. SDXL can generate images of high quality in virtually any art style and is the best open model for photorealism. It can also handle challenging concepts such as hands, text, and spatial arrangements.
ComfyUI supports SD1.x, SD2.x and SDXL models, as well as standalone VAEs and CLIP models. ComfyUI also offers many features such as embeddings, textual inversion, Loras, hypernetworks, loading and saving workflows, and image control.
The goal of this course is to help you achieve polished, professional outcomes with Stable Diffusion, SDXL and ComfyUI. You will learn how to use these tools effectively and efficiently, as well as how to fine-tune them to the demands of your work and your preferences. By the end of this course, you will be able to get the most out of the efficiency and flexibility of ComfyUI to produce reliably consistent results that begin to match the best in the industry.
Understand the purpose of the course.
How do the Pixovert ComfyUI and Stable Diffusion courses fit together.
Introduction to this section.
This lecture is core to understanding the course. Students will gain an analytical and synoptic understanding of the actions of changes in factors affecting the images. Usually explanations of CFG and its relationship with Sample Steps and the positive and negative prompts are at the level needed for understand of five-year old. But for advanced work, we need to drill down to the foundations of Stable Diffusion to understand the real roles and not just the superficial explanations
Understand the unique action and advantages of the Adaptive Sampler in ComfuUI
A newer release from Stability AI is SDXL Turbo which marks a radical break from current approaches. Based on a technique coined Adverserial Diffusion Distillation, the technique allows a distilled new version of SDXL to perform renders at breakneck speed in just 1-4 steps.
Update your installation of ComfyUI to get the new nodes for the associated workflow.
Gain an understanding of how time-based prompting can introduce compositional methods that permit the fusion of SDXL and Stable Diffusion 1.5 by allying the newer models with existing models. This extends the functional lifespan of Stable Diffusion 1.5 models and compensates for weaknesses in the SDXL models.
Perturbed Attention Guidance is a very new technique for improving detail in diffusions. The workflow may allow improved results where the refiner is not producing the kind of output that greatly improves results enough to justify the extra processing time.
SDXL can produce beautiful and detailed portraits. This lecture examines a holistic approach to creating beautiful, photorealistic portraits, making maximum use of techniques learned in the earlier parts of the course
Presenting workflows for model merging with block ratios and Lora capability.
Used in a specific way the refiner model can be used to minor fixes and enhancements to the eyes. This is a very subtle use case and one that you might have easily overlooked the potential for.
Use the noise seed to make minor adjustments in the Refiner
ChatGPT can produce an incredible range of behaviours. How can you lean into this robot to help you create detailed, inspiring prompts?
Upscaling images from Stable Diffusion 1.5 using a ControlNet is feasible even on systems that don't have the most powerful graphics cards, but the process is subject to chance alterations which can interfere with poses. In this video a controlnet is used to maintain pose whilst using latent upscale to achieve detailed, high resolution results.
OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.
Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.
Find this site helpful? Tell a friend about us.
We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.
Your purchases help us maintain our catalog and keep our servers humming without ads.
Thank you for supporting OpenCourser.