Microsoft’s FREE Bing AI Art Generator vs Midjourney V5 Direct Prompt Comparison

MattVidPro AI
21 Mar 202331:34

TLDRIn this video, the creator compares Microsoft's new Bing AI Art Generator, powered by an updated Dolly algorithm, with Midjourney V5. They discuss the capabilities and limitations of both AI art generators, highlighting the improvements in Dolly's image generation quality and variety. Despite these enhancements, Midjourney V5 maintains its edge in creating more realistic and coherent images. The creator also touches on the pricing models and accessibility of both generators, expressing excitement for the future of AI-generated art.

Takeaways

  • 🤖 Microsoft has integrated OpenAI's DALL-E algorithm into Bing as an image generator called Bing Creator, which is accessible through Microsoft's new Bing chat feature.
  • 🎨 The new DALL-E 2 algorithm has improved significantly, generating more detailed and creative imagery that is competitive with Midjourney.
  • 🌐 Users can generate images by describing what they want through a chat interface, and Bing Creator is also integrated into Microsoft Edge, marking the first browser with an integrated AI-powered image generator.
  • 📈 The updated DALL-E model has shown better performance in generating images, especially with more complex prompts, compared to the previous version.
  • 🖼️ Bing Creator provides a large image size of 1024 by 1024 pixels, offering detailed and high-quality image generation.
  • 🚀 Despite some initial issues with generating images through chat, the separate website for image generation worked well, showcasing the potential of the new algorithm.
  • 🤔 The reviewer found that the new DALL-E images sometimes lacked 'artiness' and were more realistic, which could be a subjective preference for users.
  • 🎭 In comparison tests, Midjourney V5 consistently outperformed the new DALL-E in terms of image quality and coherence, although the new DALL-E showed significant improvement over its predecessor.
  • 📱 The new DALL-E model is currently only supported in English and through Microsoft Edge, with no aspect ratio selection available yet.
  • 💡 The new DALL-E algorithm allows for an infinite number of image generations, albeit potentially at a slower pace without using a 'boost'.
  • 🌟 The reviewer highlighted that while the new DALL-E shows substantial improvement, Midjourney V5 still leads in terms of image generation quality and versatility.

Q & A

  • What is the new feature Microsoft has decided to incorporate into Bing?

    -Microsoft has decided to incorporate OpenAI's Dali algorithm into Bing, specifically through a new image generator called Bing Creator.

  • How does the new Dali algorithm compare to Midjourney in terms of image generation?

    -The new Dali algorithm appears to be competitive with Midjourney, generating detailed, creative, and visually appealing images.

  • What is the significance of the human brain processing visual information faster than text?

    -The human brain processes visual information about sixty thousand times faster than text, which is why Microsoft is focusing on creating visual tools as it's a critical way that people search for information.

  • How can users access the new Bing Creator image generator?

    -Users can access Bing Creator through Microsoft's new Bing chat feature or directly in Microsoft Edge, making it the first and only browser with an integrated AI-powered image generator.

  • What are the limitations of the new Dali 2 algorithm in terms of image generation?

    -While the new Dali 2 algorithm has improved significantly, it still lacks some features like aspect ratio adjustment and may sometimes produce images with less artistic flair and more realism.

  • How does the new Dali 2 algorithm perform when generating complex prompts like an anthropomorphic lemon character?

    -The new Dali 2 algorithm performs quite well with complex prompts, generating coherent and detailed images that combine styles and ideas effectively.

  • What is the difference between the new Dali 2 algorithm and the original Dali 2 in terms of image quality?

    -The new Dali 2 algorithm has significantly improved image quality, with higher resolution, more coherence, and sharper details compared to the original Dali 2.

  • How does the new Dali 2 algorithm compare to Midjourney V5 in generating a photo of a cat?

    -While the new Dali 2 algorithm produces realistic and detailed images of a cat, Midjourney V5 generates images that are sharper, more realistic, and have better coherency.

  • What are the unique features of the new Bing image Creator?

    -The new Bing image Creator offers AI-powered visual stories and knowledge cards, providing an engaging way to search and interact with content, including images, short videos, charts, graphs, and timelines.

  • How does the new Dali 2 algorithm handle complex artistic prompts like a 1940s detective frog?

    -The new Dali 2 algorithm handles complex artistic prompts with a high level of detail and creativity, producing images that are coherent and capture the essence of the prompt.

  • What are the limitations of the new Dali 2 algorithm when compared to Midjourney V5?

    -While the new Dali 2 algorithm has made significant improvements, it still falls short in comparison to Midjourney V5 in terms of photorealism, coherency, and handling complex artistic prompts.

Outlines

00:00

🤖 Microsoft's Integration of Dolly Algorithm into Bing

The video discusses Microsoft's collaboration with OpenAI and the incorporation of OpenAI's Dolly algorithm into Bing's image generation feature. The host expresses excitement over the new Dolly 2 algorithm, which was previously discussed in a video a few weeks prior. The algorithm is noted for its detailed and creative image generation capabilities, competitive with Mid-Journey. The host attempts to use the feature but encounters issues with Bing's chat interface. However, they successfully generate images through Microsoft Edge and compare the results with previous versions of Dolly and Mid-Journey V5, noting significant improvements.

05:02

🖼️ Comparing Dolly 2's Image Generation with Mid-Journey V5

The host compares the image generation capabilities of Dolly 2 with Mid-Journey V5 using various prompts. They note that while Dolly 2 has improved, Mid-Journey V5 still outperforms it in terms of detail and realism. The video showcases several image examples, including a crocodile, an anthropomorphic lemon character, and a black and white cat, highlighting the strengths and weaknesses of each AI model. The host also discusses the use of 'boosts' in the image generation process and how they can be replenished or redeemed with Microsoft rewards points.

10:02

🐸 Testing Character and Concept Image Generation

The video explores the AI's ability to generate complex character concepts and combines different elements to create new images. It tests the AI with a prompt for a 1940s detective frog, smoking a cigarette and wearing a detective hat. The host evaluates the results from Mid-Journey V5, Dolly 2, and the new Dolly model, noting that while Mid-Journey V5 produces the most coherent and detailed images, the new Dolly model shows significant improvement over the original Dolly 2 and provides a more realistic and sharp output.

15:04

🐱 Further Analysis of Dolly's Image Generation Quality

The host continues to analyze the image generation quality of the new Dolly model using prompts involving cats and road signs. They compare the results with the original Dolly 2 and Mid-Journey V5, observing that the new Dolly model has made strides in realism and detail, although it still has some inconsistencies. The video also touches on the artistic aspects of the generated images, noting that while they may not always be photorealistic, they possess a certain artistic quality.

20:06

🕵️‍♂️ Assessing Dolly's Ability to Generate Detailed Characters

The video script focuses on the AI's capability to generate detailed and artistic character concepts. It presents a prompt for a 'Walter White Lego character' and evaluates the results from Mid-Journey V5 and the updated Dolly model. The host finds that while Mid-Journey V5 produces highly realistic and detailed images, the new Dolly model also delivers improved and coherent results, particularly in rendering the character's features and the Lego set concept.

25:07

📸 Reviewing Dolly's Performance in Various Image Prompts

The host reviews the performance of the new Dolly model across a range of image prompts, including a business interview setup with a shitzu, a skateboarding penguin, and a shitsu on a pirate ship. The results are compared with the original Dolly 2 and Mid-Journey V5. While the new Dolly model does not match the quality of Mid-Journey V5, it demonstrates significant improvement over its predecessor. The video concludes with a discussion on the new pricing model of the Dolly model, which offers free credits and effectively unlimited image generations, albeit with potential delays for additional 'fast credits'.

30:08

📈 Conclusion and Viewer Engagement

The host concludes the video by summarizing the improvements of the new Dolly model over the original Dolly 2 and invites viewer opinions on its competitiveness with Mid-Journey V5 and other fine-tuned models. They also discuss the new pricing strategy, which provides free credits weekly and theoretically allows for infinite image generations, albeit with longer wait times without additional credits. The host thanks the viewers for their support and engagement.

Mindmap

Keywords

💡Bing AI Art Generator

The Bing AI Art Generator is a feature incorporated by Microsoft into its Bing search engine. It utilizes the Dolly algorithm, developed by OpenAI, to generate images based on textual prompts provided by users. This tool is showcased as competitive with other image generation models and is a central focus of the video, demonstrating its capabilities through various prompts and comparisons.

💡Midjourney V5

Midjourney V5 refers to the fifth version of an AI image generation model by Midjourney, a company specializing in AI technology. The video compares the output and capabilities of Midjourney V5 with the Bing AI Art Generator. It is noted for its high-quality, photorealistic image generation and is considered a benchmark for comparison in the video.

💡Dolly Algorithm

The Dolly algorithm is an AI model used for generating detailed and creative imagery. It is mentioned as being integrated into Bing's image generation feature. The video discusses the improvements made in the newer version of the Dolly algorithm, highlighting its competitive edge with other models like Midjourney V5.

💡Image Generation

Image generation is the process of creating visual content from textual descriptions using AI algorithms. The video script discusses the advancements in image generation technology, particularly focusing on how the Bing AI Art Generator and Midjourney V5 perform against each other in creating detailed and coherent images from given prompts.

💡AI Powered Visual Stories

AI powered visual stories refer to the use of artificial intelligence to create narratives that are visually engaging. In the context of the video, Microsoft's Bing Image Creator is described as being capable of generating both written and visual content, enhancing the user's search experience with a more interactive and visually rich interface.

💡GPT4

GPT4, or Generative Pre-trained Transformer 4, is an advanced AI language model that is part of the larger GPT family developed by OpenAI. The Bing chatbot AI uses a version of GPT4, which is significant as it allows for more sophisticated and human-like text generation, contributing to the chat feature's ability to understand and respond to user prompts.

💡Photorealism

Photorealism in the context of AI image generation refers to the ability of an AI model to produce images that closely resemble photographs. The video compares the photorealistic qualities of the images generated by Bing AI Art Generator and Midjourney V5, noting the level of detail and realism as a key differentiator between the models.

💡Creative Mode

Creative mode, as mentioned in the script, is a setting within the Bing Image Creator that allows users to generate images with a focus on artistic and innovative outputs. The video explores the use of creative mode to produce unique and detailed images, emphasizing the model's capability to understand and execute complex prompts.

💡Microsoft Edge

Microsoft Edge is a web browser developed by Microsoft. The video highlights that the Bing Image Creator feature is integrated into Microsoft Edge, making it the first and only browser with an integrated AI-powered image generator. This integration is presented as a significant development in enhancing the browser's capabilities.

💡Stable Diffusion

Stable Diffusion is an AI model used for generating images from text descriptions. Although not directly mentioned in the video's main content, the term is alluded to when the narrator speculates about the existence of plugins that could add similar functionalities to other browsers like Chrome. It represents the broader context of AI image generation models that the video is discussing.

💡Aspect Ratio

Aspect ratio refers to the proportional relationship between the width and height of an image. The video notes the absence of aspect ratio options in the new Dolly 2 model within the Bing Image Creator, which is a feature that was available in the original Dolly and is also available in Midjourney V5, indicating a limitation in the new model's capabilities.

Highlights

Microsoft has integrated OpenAI's DALL-E algorithm into Bing as an image generator called Bing Creator.

The new DALL-E algorithm, referred to as Dolly 2, produces high-quality and detailed imagery.

Bing Creator is accessible through Microsoft's new Bing chat feature.

The integration of Bing image Creator is a new feature announced on the same day of the video.

The human brain processes visual information much faster than text, which is why Bing is focusing on visual tools.

Bing Creator is initially rolling out in 'creative mode' and is also available in Microsoft Edge.

The updated Dolly algorithm generates images at a resolution of 1024 by 1024.

The new Dolly algorithm's image quality is significantly better than the previous version.

Bing Creator allows for infinite image generation, albeit at potentially slower speeds without a 'boost'.

The new Dolly algorithm can create more complex and coherent images, such as anthropomorphic characters.

Midjourney V5 outperforms the new Dolly in terms of image quality and realism.

Bing Creator's images sometimes lack artistic flair and are more realistic compared to Midjourney V5.

Midjourney V5 provides more photorealistic images, closely resembling actual photography.

The new Dolly algorithm has improved significantly but still has room for enhancement in certain areas.

Bing Creator offers a more accessible and free alternative to paid models like Midjourney, despite slower generation times without boosts.

The new Dolly algorithm struggles with generating images of people smoking, a common challenge for AI image generators.

Bing Creator's updates have led to more detailed and less blotchy images compared to the original Dolly 2.

The character and detail in the new Dolly-generated images are significantly improved, showing a major step forward for the model.