
Introduce major AI image generator platforms and compare ease of use, interfaces, and image editing features such as image to image, inpainting, and outpainting.
Follow guided experiential learning by actively doing alongside the instructor, and explore beyond the lesson while engaging the platform and asking questions in the Q&A community.
Explore AI image editing platforms with image generation, comparing tools like clip drop and Runway across outpainting, inpainting, image variations, background removal, upscaling, and color edits.
Explore how DALL-E uses diffusion to generate images from prompts, with inpainting and outpainting options, optional editing, and style variety, while noting square outputs and photorealism limits.
Explore image generation with Dali, crafting prompts to produce surreal, photorealistic images using outpainting, inpainting, variations, and gallery styles. Learn login, prompt tips, and how to iterate with examples.
Compare DALL-E 3 with Bing and DALL-E 3 with ChatGPT to explore image generation workflows, boosts, and limitations in Bing Image Creator, prompts, four-image outputs, and chat integration.
Explore DALL-E 3 integration with ChatGPT-4 to generate and edit images from text prompts, upload and analyze reference images, and produce variants in landscape, portrait, or square formats.
Learn prompt writing for stable diffusion tools, shaping images by subject, medium, and art style, and apply negative prompts to avoid cropped or not safe for work results.
Use negative prompts to avoid bad framing, anatomy errors, and artifacts, then enhance with background, lighting, and realism terms like Unreal Engine and Octane Render.
Master prompt order to influence outcomes, prioritizing beginning and end words. Learn to weight key terms with parentheses for a Cleopatra-inspired ancient Egypt portrait.
Craft landscape prompts of a medieval castle in a forest with a floating sky castle, in an oil painting style, magical and epic fantasy, use artist references and keyword weights.
Explore resources for prompt writing, including keyword guides and modifiers. Learn model-specific vocab from Stable Diffusion and Midjourney, plus prompts from Prompt Hero and Lexica.
Explore Lexica, an image generator and image search engine with aperture version 2 and version 3 models, offering image-to-image generation, private options on paid plans, and licensing considerations.
Explore Lexica features, including the search engine, like gallery, saved styles, and style or object searches, then edit with prompts, generate variations, and out painting for refined AI art.
Explore AI image generation for logos, illustrations, landscapes, and concept art. Adjust prompts, styles, and guidance scale, and use negative prompts to control color and detail.
Explore how guidance scale influences AI art prompts and outputs, using a girl with a kitten at a bus station to show details, artifacts, and color.
Explore stable diffusion, an open source image generator by Stability AI, and learn Dream Studio's web app for image generation and editing, including inpainting and outpainting, prompts, and usage models.
Discover Blue Willow, an image generator that aggregates multiple models, including Stable Diffusion, selects the best model for your prompt, and lets you upscale, vary, and outpaint images on Discord.
Explore how to control image generation with aspect ratio settings, prompts, and model versions, including portrait and landscape outputs, negative prompts, upscaling, and outpainting.
Learn image-to-image generation with Blue Willow by using a linked image, crafting prompts, and setting aspect ratio, version, and negative prompts for detailed, stylized outputs.
Explore how Midjourney, an image generator, creates highly realistic images and supports beginner prompts, upscaling, variations, image-to-image generation, and emoji prompts, with private mode on pro plans.
Set up Midjourney on Discord, choose a plan, and master basic commands like /imagine, /info, and /settings to create art with public or private modes.
Master text-to-image generation with Midjourney by learning prompts, upscaling, variations, and negative prompts, and control aspect ratio across versions to craft diverse outputs.
Explore the blend function in image-to-image generation, blending up to five uploaded images into a new composite without prompts, then compare with prompt-based results using configurable dimensions.
Upload your image and run slash describe to generate prompts and keywords such as surrealistic, grotesque, and illusionistic detail.
Learn how Midjourney parameters image weight, quality, and stop shape generated images by balancing prompt versus image influence, detail and speed, and progression for sharper results.
Explore Midjourney models and versions, from 5.2 to 5.1 and older, noting how each version alters realism and anime or illustration styles, and how to switch via prompts or settings.
Understand Midjourney stylize values across version 5.2, from low to very high, to balance prompt fidelity and artistic detail. Use dash stylize or dash s with examples.
Explore logo design with Midjourney AI prompts, crafting minimalist vector logos such as a cupcake with a cherry, using white backgrounds, text, and variations through chaos settings and two-color palettes.
Explore magical realism through 3d renders, anime characters, and landscapes using Midjourney and Niji prompts, with upscaling and outpainting tips.
Discover Midjourney's November 2023 updates: tune command and style tuner for targeted styles, plus upscaling, editing with inpainting, and the weird parameter for creative variation.
Explore simple ai photo editing tools like bigjpg.com for image upscaling with noise reduction and vectorizer.ai for converting jpeg or png to svg, plus creator kit for e-commerce background generation.
Learn to use the creator kit for ecommerce to place your product in themed backgrounds by uploading images, selecting styles, and crafting prompts for compelling visuals.
Explore Clip Drop, an AI-powered ecosystem for creators that generates and edits images using stable diffusion, outpainting, reimagine, cleanup, background removal, lighting adjustments, upscaling, and background replacement.
Explore clip drop's text remover tool to automatically remove text from logos, slogans, mockups, and product images, with notes on limitations and the complementary cleanup tool.
COURSE UPDATE!!!
Our DALL-E and Midjourney sections just got a major upgrade!
New videos have been added, spilling the beans on DALL-E 3! Find out what's different, see cool ways it's used, and learn how it buddies up with ChatGPT-4. Plus, peek into the ring with DALL-E 3 with Bing vs. ChatGPT and uncover the Gen_ID parameter.
Delve into the latest features of Midjourney, including the revolutionary "/tune command." Master the art of upscaling, refine your editing skills, and venture into the uncharted territory of --weird parameter.
Don't just learn one AI Art Generation tool - learn them all!
Become a well-rounded AI Artist and Learn the most popular 12+ AI Art Tools, Midjourney, DALL-E, and more.
We go through all the most popular AI Art Tools: Midjourney, DALL-E, Lexica, Dreamstudio, BlueWillow, ClipDrop, Adobe Firefly, RunwayML, Leonardo AI, Astria AI, and Automatic1111 (SD).
Why learn all AI Art Generation tools instead of just one?
Midjourney is great for photorealistic images, but is not at all for inpainting. For that, you can use Leonardo, but that's not image customization. For that, you should use Stable Diffusion (Automatic1111) libraries. How about if you need to upscale, relight, or edit? Then ClipDrop is the way to go? Get my drift? Different tools do different things - so to become a well-rounded AI Artist - you should learn them all!
Embark on an exhilarating journey through the captivating world of AI Art Generation in this comprehensive 11-hour plus course that ignites your creativity.
Explore groundbreaking technologies such as DALL-E, and Stable Diffusion (SD), that reshape the art-making process. Delve into the realm of basic AI Photo editing tools and unlock the full potential of ClipDrop, Adobe Firefly, RunwayML, Leonardo AI, and AUTOMATIC1111 to create awe-inspiring visual masterpieces.
Unleash the full force of your creativity and watch your imagination come to life with the incredible power of AI.
What is this course all about?
Our primary goal is to teach you not just one, but all the AI Art generation tools (like Midjourney, Stable Diffusion, and more). We equip you with a deep understanding of various AI image generation and editing technologies, enabling you to take your artistry to new heights.
What is AI Art Generation?
AI art generation is the process of creating art and images using artificial intelligence (AI). This technique entails using AI algorithms and machine learning to help produce art and image (like Midjourney and Stable Diffusion). AI art generators are trained on large image datasets to learn the correlations between colors, forms, and other visual components. As a result, they can develop new sets of images, such as new artworks, imitate existing styles, or add artistic features to images.
Why learn all AI Art Generation tools instead of just one?
Midjourney is great for photorealistic images, but is not at all for inpainting. For that, you can use Leonardo, but that's not image customization. For that, you should use Stable Diffusion (Automatic1111) libraries. How about if you need to upscale, relight, or edit? Then ClipDrop is the way to go? Get my drift? Different tools do different things - so to become a well rounded AI Artist - you should learn them all!
Who are the instructors for this course?
· Henry Habib - A data and AI professional and an advocate of no-code development and AI education who has impacted the lives of over 100,000+ students by offering diverse courses to share his knowledge and expertise.
· Katerina Antonenko (from The Intelligent Worker) - An AI professional with a unique blend of expertise in natural science and computer science. Currently based in Canada, she's busy crafting animated and educational videos for tech firms, with a specialization in decentralized technology, artificial intelligence, and crypto. Beyond her technical pursuits, she has a deep love of art and creativity, finding satisfaction in creating stunning digital artworks and expressing herself through the timeless medium of oil paints.
Why choose this course?
· Comprehensive Coverage: This course delves into many elements of AI art generation, including picture generation, image manipulation, outpainting, image-to-image generation, prompt writing methodologies, advanced settings, and model training, which ensures an in-depth understanding of each AI image generation platform.
· Diverse AI Art Generation Tools: The course covers a wide range of AI art generation tools, including DALL-E, Images ai, Lexica ai, DreamStudio, BlueWillow, Midjourney, ClipDrop, Adobe FireFly, RunwayML, Leonardo ai, Astria ai, and AUTOMATIC1111 which gives students a thorough understanding of numerous AI-based artistic techniques and applications.
· Industry-standard Software: Many of the tools and platforms covered in the course, such as Adobe FireFly and RunwayML, are extensively used in the creative industry, providing learners with significant experience with industry-standard software.
· Real-world Applications: In addition to focusing on artistic creativity, the course illustrates practical applications in tasks such as photo editing, background removal, recoloring, text effects, and more, making it applicable to graphic design and other industries.
· Instructor Assistance: The course provides instructor assistance, allowing students to seek guidance, clarification, and feedback from our instructors at any time during their learning journey.
Course Overview:
· Introduction: The course introduction gives an overview of the curriculum, including roadmaps and a full comparison of all of the AI image-generating tools that will be taught. Learners are also introduced to the instructors, who will guide and support them during the course.
· DALL-E: This section covers an introduction to the platform and its capabilities, as well as image generation, editing techniques, outpainting, prompt writing examples, and useful resources for effective prompt creation.
· Prompt Writing: The section tackles prompt writing approaches such as subject and medium, composition, action, details, negative prompts, stylizers, and portrait and landscape examples, as well as supplementary resources for effective prompt creation.
· Lexica art: Explores the features of Lexica art, including image generation for portrait, logo, cartoon, and sci-fi, utilizing the prompt guidance parameter and image-to-image generation capabilities.
· DreamStudio AI: Introduces learners to its features and models, offering a platform for image generation with the use of seed parameters for creative exploration.
· BlueWillow: Covers an introduction to BlueWillow, including Discord setup and an overview of its features. It also delves into image generation, as well as image-to-image generation techniques.
· Midjourney: This section offers a comprehensive introduction to Midjourney, covering its setup, basic commands, and various functionalities. It also includes diverse examples, allowing learners to experiment with artistic creations across various styles.
· AI Photo Editing Tools: Explore the world of basic AI photo editing with tools like bigjpg, vectorize, segment-anything, and creatorkit for enhancing your creative projects.
· ClipDrop: Covers ClipDrop overview and editing features.
· Adobe Firefly: Provides an in-depth understanding of its features and editing capabilities.
· RunwayML: Offers a comprehensive explanation of AI art generation techniques, covering text-to-image and image-to-image generation, as well as training custom generators. Participants will learn to expand and manipulate images with features like frame interpolation, backdrop remix, upscale image, and 3D texture manipulation.
· Leonardo AI: Introduces learners to Leonardo, providing an overview of its image generation capabilities in both txt-to-img and img-to-img modes. Students will explore Leonardo's parameters for generating images, as well as techniques for outpainting and inpainting using AI Canvas.
· Astria AI: Learners will be introduced to the concept of model training.
· AUTOMATIC1111: Provides a complete overview, covering setup in Google Colab and RunDiffusion, along with exploring basic and advanced parameters and other functionalities.
· Project: A bonus section of the course that offers exciting opportunities to explore AI-generated creativity, including creating a comic book version of oneself with Astria AI and A1111, designing a book cover with Midjourney and A1111, and crafting a logo using Midjourney, Leonardo, Clipdrop, Vectorizer, and Firefly.