BEST AI Art Generator? Dall E 2 vs Midjourney vs Stable Diffusion

Wade McMaster - Creator Impact
22 Dec 202207:04

TLDRThe video script offers a comparative analysis of three AI art platforms: Dolly 2, Mid-Journey, and Stable Diffusion. It evaluates their performance based on various prompts, highlighting the distinct styles each platform produces. Dolly 2 is noted for its photorealistic images, Mid-Journey for its artistic and appealing compositions, and Stable Diffusion for its photorealistic attempts, though sometimes less impressive. The ease of use and features of each platform are also discussed, with Dolly 2 having a user-friendly interface and Mid-Journey offering a more complex experience on Discord. The video encourages viewers to share their preferences and experiences with these platforms.

Takeaways

  • 🎨 Three main AI art platforms discussed: Dolly 2, Mid-Journey, and Stable Diffusion.
  • 🖼️ Dolly 2 produces almost photorealistic images with a slight imperfection in teeth appearance.
  • 🌟 Mid-Journey delivers stunning, non-photorealistic art with a unique artistic style.
  • 📈 Stable Diffusion provides decent results but ranks third among the three in this comparison.
  • 👁️‍🗨️ Vision prep is favored for the best-looking image, while Dolly 2 has the most realistic photorealistic image.
  • 🎨 Dolly 2's oil painting of a Shaolin monk is standard, Mid-Journey's is sharp and exciting, and Stable Diffusion's is traditional.
  • ☀️ Sunny outdoor scenes by Dolly 2 resemble photographs, Mid-Journey opts for an artistic painting style, and Stable Diffusion chooses a photo look.
  • 🏙️ Busy city street scenes vary in style, with Dolly 2 combining painting and photography, Mid-Journey being more striking, and Stable Diffusion maintaining a photorealistic approach.
  • 🤖 Cyborg with glowing eyes is depicted in a simple style by Dolly 2, an impressive video game style by Mid-Journey, and a cool but less glowing version by Stable Diffusion.
  • 🐶 A cute puppy wearing sunglasses and headphones is portrayed realistically by Dolly 2, with more artistic depth by Mid-Journey, and a realistic photo look by Stable Diffusion.
  • 🐢 3D render of a turtle is plain but recognizable in Dolly 2, more detailed and impressive in Mid-Journey, and better than Dolly 2 but with a boring background in Stable Diffusion.
  • 🐉 Ink sketch of a dragon is rough yet cool in style by Dolly 2, more photo-like and detailed by Mid-Journey, and neater and cohesive by Stable Diffusion.
  • 💼 Businessman photograph is best captured by Dolly 2 in terms of photorealism, while Mid-Journey and Stable Diffusion have some flaws in facial elements.

Q & A

  • What are the three main AI art platforms mentioned in the transcript?

    -The three main AI art platforms mentioned are Dolly 2, Mid Journey, and Stable Diffusion.

  • How does the transcript describe the image of a beautiful woman with blue eyes created by Dali 2?

    -The image created by Dali 2 is described as almost photorealistic, with the only issue being that the teeth look a little bit funny.

  • What style of image did Mid Journey produce for the Shaolin monk prompt?

    -Mid Journey produced an image that looks like a high-quality oil painting, which is visually stunning and sharp.

  • How does the narrator prefer the image of the sunny outdoor scene created by which platform?

    -The narrator prefers the image of the sunny outdoor scene created by Mid Journey, as it is described as an artistic masterpiece with a painting style.

  • What is the narrator's overall opinion on the cyborg with glowing eyes created by the platforms?

    -The narrator prefers the cyborg image created by Mid Journey, as it is described as really impressive with a video game style, while Dali 2's version was simpler and Stable Diffusion's eyes were not glowing as requested.

  • Which platform is mentioned as having a nicer interface and useful features like in painting and out painting?

    -Dali 2 is mentioned as having a nicer interface with features like in painting and out painting, which allows users to add more AI art into specific areas.

  • What is the main advantage of using Stable Diffusion according to the transcript?

    -The main advantage of using Stable Diffusion, as mentioned in the transcript, is that it is available for free, although it might be the most complex to set up.

  • How does the transcript describe the 3D render of a turtle created by Mid Journey?

    -The 3D render of a turtle created by Mid Journey is described as being on another level compared to the simpler 3D render created by Dali 2, with more depth and a more impressive scene.

  • Which platform tends to produce more artistic and better composed images according to the narrator?

    -According to the narrator, Mid Journey tends to produce more artistic and better composed images compared to the other platforms.

  • What is the narrator's preferred platform for creating images based on the transcript?

    -The narrator's preferred platform for creating images, as concluded in the transcript, is Mid Journey due to its artistic style and better composition.

  • What does the narrator suggest at the end of the transcript for viewers to do?

    -The narrator suggests that viewers should share their thoughts and preferences in the comments below the video, and discuss which platform they would choose to use for creating AI art.

Outlines

00:00

🎨 Comparison of AI Art Platforms

This paragraph discusses the comparison of three main AI art platforms: Dolly 2, Mid-Journey, and Stable Diffusion. The comparison is based on the results produced by each platform when given the same basic prompts. The platforms are evaluated on their ability to create photorealistic images, artistic styles, and overall visual appeal. Dolly 2 is noted for its photorealistic images, Mid-Journey for its artistic and striking visuals, and Stable Diffusion for its standard oil painting and photo look. The paragraph emphasizes that while there is skill involved in getting desired results, the platforms show promise in their respective areas.

05:01

🖼️ Artistic Interpretations and Platform Analysis

The second paragraph delves deeper into the artistic interpretations of the AI platforms, focusing on the variety of styles and the strengths of each. It discusses the creation of an oil painting of a Shaolin monk, a sunny outdoor scene, a busy city street, a cyborg with glowing eyes, and a cute puppy wearing sunglasses and headphones. The platforms are evaluated based on their ability to capture the essence of the subjects and their artistic expression. The paragraph also touches on the user interface and usability of the platforms, with Dolly 2 noted for its user-friendly interface, Mid-Journey for its complex but rewarding imagery, and Stable Diffusion for its free availability but complex setup.

Mindmap

Keywords

💡AI art platforms

AI art platforms refer to online services or software that utilize artificial intelligence to generate or enhance digital art. In the context of the video, three specific platforms are mentioned: Dolly 2, Mid-Journey, and Stable Diffusion. These platforms are used by artists and enthusiasts to create various styles of images by inputting prompts or descriptions.

💡Photorealistic

Photorealistic refers to images or artwork that closely resemble real-life photographs in terms of detail, lighting, and texture. In the video, the term is used to describe the quality of the AI-generated images, particularly when they mimic the appearance of actual photographs.

💡Artistic style

Artistic style encompasses the unique visual characteristics and techniques used by an artist or AI platform to create a piece of art. It can include elements such as color palette, brush strokes, and composition. In the context of the video, the artistic style is a crucial factor in evaluating the output of the AI art platforms.

💡3D render

3D render refers to the process of generating a two-dimensional image from a three-dimensional model. This process involves calculating and processing the appearance of objects in a 3D scene based on lighting, materials, and the viewer's perspective. In the video, the term is used to describe the AI-generated images that have a three-dimensional look.

💡Ink sketch

An ink sketch is a type of drawing typically done with ink and characterized by bold lines and varying degrees of shading. It is a traditional art form that can be used to create quick, expressive drawings or more detailed illustrations. In the video, the term refers to the style of AI-generated art that mimics the appearance of ink sketches.

💡User interface

User interface refers to the point of interaction between a user and a computer system or software. It includes the design, layout, and functionality of the system that allows users to navigate and use the platform effectively. A user-friendly interface can greatly enhance the experience of using an AI art platform.

💡Art composition

Art composition refers to the arrangement of visual elements within an artwork to create a unified and aesthetically pleasing image. It involves decisions about the placement, balance, and interaction of objects, colors, and shapes within the frame. In the context of the video, art composition is a critical aspect when evaluating the quality and appeal of the AI-generated images.

💡Photorealism

Photorealism is an art movement that involves creating images or paintings that closely imitate the appearance of photographs. It is characterized by a high degree of detail and a focus on accurately replicating the visual aspects of reality. In the context of the video, photorealism is used to describe the AI-generated images that closely resemble real-life photographs.

💡Artistic expression

Artistic expression is the process of conveying emotions, ideas, or concepts through various art forms. It allows artists to communicate their vision and creativity in unique and personal ways. In the video, the term relates to the different styles and approaches each AI platform uses to express the prompts given to them.

💡Image resolution

Image resolution refers to the number of pixels that make up the dimensions of an image. A higher resolution, such as 1024 by 1024 pixels, means more detail and clarity in the image. In the context of the video, image resolution is an important factor in determining the quality and usability of the AI-generated art.

Highlights

Three main AI art platforms are compared: Dolly 2, Mid Journey, and Stable Diffusion.

Dolly 2 creates almost photorealistic images with some minor imperfections.

Mid Journey produces stunning images, though not as photorealistic as Dolly 2.

Stable Diffusion provides decent images but is considered the weakest among the three.

Vision prep is noted as the best-looking image, and Dolly has the most realistic photorealistic image.

Dolly 2's oil painting of a Shaolin monk looks standard, while Mid Journey's is sharp and exciting.

Stable Diffusion's oil painting of a Shaolin monk is standard but still visually appealing.

Mid Journey creates an artistic masterpiece for a sunny outdoor scene.

Stable Diffusion opts for a more photo-like look for the outdoor scene, differing from Mid Journey's painting style.

Dolly 2's image of a busy city street combines painted and photographic elements.

Mid Journey's city street image is striking and artistic, with vibrant colors.

Stable Diffusion's city street image is photo-like but lacks the artistic flair of Mid Journey.

Dolly 2's cyborg with glowing eyes is simple and in a video game style.

Mid Journey's cyborg is impressive and crazy, standing out with a unique style.

Stable Diffusion's cyborg is decent but the eyes aren't as glowing as desired.

Dolly 2's 3D render of a turtle is plain but 3D-looking.

Mid Journey's 3D turtle render is on another level, more detailed and impressive.

Stable Diffusion's 3D turtle render is better than Dolly 2's but has a boring background.

Dolly 2's ink sketch of a dragon is rough but cool for the style.

Mid Journey's ink drawing is next level and very detailed.

Stable Diffusion's dragon sketch is neater and cohesive, but may not be what some are looking for.

Dali 2 wins in photo realism, Mid Journey in artistic composition, and Stable Diffusion in creating photorealistic images.

Dolly 2 has a user-friendly interface with features like in painting and out painting.

Mid Journey has a more complex interface but produces better imagery.

Stable Diffusion is free and can be complex to set up, with online interfaces available.

The video invites viewers to share their thoughts and preferences regarding the AI art platforms.