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: Dali 2, Mid-Journey, and Stable Diffusion. It evaluates their performance based on various prompts, highlighting the distinct styles each platform produces. Dali 2 is noted for its photorealistic images, Mid-Journey for its artistic and striking compositions, and Stable Diffusion for its photorealistic attempts, though sometimes less impressive. The user interface and ease of use are also discussed, with Dali 2 having a more user-friendly interface and Mid-Journey offering higher-quality imagery despite its complexity. 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 rendering.
  • 🌟 Mid-Journey delivers stunning, artistic images that are not as photorealistic but have a unique style.
  • 📸 Stable Diffusion provides decent results but is considered the weakest among the three in the tested version.
  • 👁️‍🗨️ The platforms respond differently to prompts, offering varied styles and levels of photorealism.
  • 🎨 Dolly 2's interface is user-friendly with features like in-painting and out-painting.
  • 🤖 Mid-Journey is more complex to use but offers higher quality imagery.
  • 🆓 Stable Diffusion is available for free but has a steeper learning curve for setup.
  • 📈 Dolly 2 excels in photorealism, Mid-Journey in artistic composition, and Stable Diffusion in photorealistic images.
  • 📱 The choice of platform depends on the user's preference for photorealism, artistic style, and ease of use.
  • 📊 The video invites viewers to share their preferences and experiences with the AI art platforms.

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 narrator describe the initial result from Dolly 2 with the prompt of a beautiful woman with blue eyes?

    -The narrator describes the Dolly 2 result as almost photorealistic, with the teeth looking a bit funny.

  • What style does the narrator prefer for the oil painting of a Shaolin monk?

    -The narrator prefers the Mid Journey image for its cooler style and more artistic approach, as opposed to the more traditional look of the other platforms.

  • Which platform produced the most realistic photo-like image for the sunny outdoor scene?

    -Dolly 2 produced the most realistic photo-like image for the sunny outdoor scene.

  • What is the narrator's overall preference for the cyborg with glowing eyes prompt?

    -The narrator prefers the Mid Journey result for its creative and impressive video game style.

  • How does the narrator compare the 3D render of a turtle from the three platforms?

    -The narrator finds Dolly 2's turtle to look plain but 3D, Mid Journey's render to be on another level, and Stable Diffusion's turtle to have a better 3D look but with a boring background.

  • Which platform won the photo realism category according to the narrator?

    -Dolly 2 won the photo realism category according to the narrator.

  • What interface advantages does Dolly 2 have over the other platforms?

    -Dolly 2 has a nicer and easier-to-use interface with features like in painting and out painting, allowing for more AI art to be added to specific areas.

  • What is the narrator's final verdict on the platforms?

    -The narrator concludes that Dolly 2 has the most photorealistic images, Mid Journey tends to have more artistic and better composed images, and Stable Diffusion is better at creating photorealistic images but is second to both in the narrator's opinion.

  • What resolution images do the platforms produce according to the narrator?

    -Dolly 2 and Mid Journey produce 1024 by 1024 pixel images, while the version of Stable Diffusion used was smaller but potentially adjustable.

  • How can users share their thoughts on the platforms discussed in the transcript?

    -Users can share their thoughts and preferences by leaving a comment below the video.

Outlines

00:00

🎨 Comparison of AI Art Platforms: Dolly 2, Mid-Journey, and Stable Diffusion

The paragraph discusses a comparison of three main AI art platforms: Dolly 2, Mid-Journey, and Stable Diffusion. The author provides a hands-on evaluation by inputting basic prompts into each platform to assess their performance and style output. The platforms are critiqued based on their ability to create photorealistic images, artistic styles, and overall visual appeal. Dolly 2 is noted for its photorealistic quality, Mid-Journey for its artistic and striking imagery, and Stable Diffusion for its standard oil painting and photo look. The author also comments on the user interface and usability of each platform, with Dolly 2 having a more user-friendly interface and Mid-Journey offering a more complex setup through Discord. Stable Diffusion is mentioned as being freely available but with a more complex setup process.

05:01

🖼️ Artistic Interpretations: Dolly 2 vs Mid-Journey vs Stable Diffusion

This paragraph continues the discussion on AI art platforms, focusing on the artistic interpretations of various prompts by Dolly 2, Mid-Journey, and Stable Diffusion. The author compares the platforms' outputs for different subjects, such as a Shaolin monk, a sunny outdoor scene, a busy city street, a cyborg, a cute puppy, a 3D render of a turtle, and an ink sketch of a dragon. The comparison highlights the unique styles and levels of detail each platform offers, with Mid-Journey often praised for its artistic depth and impressive imagery. The author also notes the photorealistic strengths of Dolly 2 and Stable Diffusion's more traditional looks. The paragraph concludes with a call to action for viewers to share their preferences and thoughts on the platforms discussed.

Mindmap

Keywords

💡AI art platforms

AI art platforms refer to online services or software that utilize artificial intelligence to generate or assist in creating artworks. In the context of the video, three specific platforms are mentioned: Dolly 2, Mid-Journey, and Stable Diffusion. These platforms are used to compare the quality and style of AI-generated art based on user-provided prompts.

💡Photorealistic

Photorealistic refers to images or artworks that are created to closely resemble photographs, aiming to replicate the detail and appearance of real-world scenes or objects. In the video, the term is used to describe the level of realism achieved by the AI platforms, particularly when comparing the outputs of Dolly 2.

💡Oil painting

An oil painting is a traditional art form where paint made from pigments mixed with oil is applied to a canvas or other surface. In the video, the term is used to describe the style of AI-generated art that emulates the appearance of oil paintings, as seen in the outputs from Dolly 2 and Mid-Journey.

💡Cyborg

A cyborg, short for cybernetic organism, is a being with both organic and artificial components, often seen in science fiction. In the video, the term is used as a prompt for the AI platforms to generate an image of a cyborg with glowing eyes, showcasing the platforms' ability to create imaginative and futuristic concepts.

💡3D render

A 3D render is the process of generating a two-dimensional image or animation from a three-dimensional model using computer graphics software. In the video, the term is used to describe the type of output the AI platforms are asked to create, specifically a 3D render of a turtle, to demonstrate their capability in producing depth and dimension in their artworks.

💡Ink sketch

An ink sketch is a drawing made with ink, often characterized by bold lines and shading. In the video, the term is used to describe the style of AI-generated art that mimics the appearance of hand-drawn sketches, particularly in the context of creating an ink sketch of a dragon.

💡Businessman

A businessman is a professional who works in the business sector, often involved in commerce, trade, or management. In the video, the term is used as a subject for the AI platforms to create a photograph-like image, testing their ability to capture realistic human portraits.

💡Interface

In the context of software and technology, an interface refers to the point of interaction between a user and a computer program or system. The video discusses the ease of use and features of the interfaces of the AI art platforms, highlighting the user experience when interacting with Dolly 2, Mid-Journey, and Stable Diffusion.

💡Artistic composition

Artistic composition refers to the arrangement of visual elements within an artwork to create a harmonious and engaging piece. In the video, the term is used to evaluate the quality of the AI-generated images, particularly in how Mid-Journey tends to produce more artistically composed and visually appealing outputs compared to the other platforms.

💡Photorealism

Photorealism is an art movement characterized by the creation of artworks that are virtually indistinguishable from photographs. In the context of the video, photorealism is used to describe the level of realism achieved by the AI platforms, especially when discussing the outputs of Dolly 2 and Stable Diffusion.

💡User prompts

User prompts are the input or instructions given to AI platforms to guide the generation of specific content. In the video, user prompts are the basis for comparing the results of the AI art platforms, as they are used to evaluate how each platform interprets and visualizes the same request.

Highlights

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

Dolly 2 creates almost photorealistic images with some minor quirks.

Mid-Journey produces stunning images, though not as photorealistic.

Stable Diffusion provides decent results but may not be the best among the three.

Vision prep is considered the best looking image, while Dolly has the most realistic photorealistic image.

Mid-Journey's Shaolin monk oil painting is sharp, fantastic, and exciting.

Stable Diffusion's oil painting is standard but still cool.

Dolly 2's sunny outdoor scene is very photo-like but not the most appealing.

Mid-Journey's artistic masterpiece has a painting style, favored over Stable Diffusion's photo look.

Dolly 2's busy city street image combines painted and photographic looks.

Mid-Journey's striking and artistic city street image is preferred over Stable Diffusion's photo-like approach.

Dolly 2's cyborg with glowing eyes is simple but cool, though not what was expected.

Mid-Journey's cyborg is impressive with a video game style.

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

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

Mid-Journey's 3D turtle render is on another level, more 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 photo opening drawing of a dragon is next level and very cool.

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

Dali 2 wins the photo realism, Mid-Journey has the best look, and Stable Diffusion is better at photorealistic images but still second to both.

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

Mid-Journey is more complex to use with Discord but produces better imagery.

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