Midjourney is Free Again... and here's why.

Matt Wolfe
22 Aug 202422:40

TLDRThe AI image generation landscape is rapidly evolving with new models like Idiogram 2.0 offering free access, prompting platforms like Midjourney to provide free trials. A comparative analysis of various AI models including Idiogram, Midjourney, Freepick's Mystic, and Leonardo's Phoenix reveals strengths in areas like realism, text incorporation, and prompt adherence. As competition grows, consumers benefit from a range of free and high-quality options, making it easier to turn creative visions into digital art.

Takeaways

  • 🌐 AI image generation has seen significant innovation, with models like grock 2 generating realistic images, excluding adult content.
  • 🔍 Underneath, grock 2 utilizes the flux one model from Black Forest labs, which has been extensively used and reviewed in recent videos.
  • 🆓 This week saw the release of idiogram 2.0, a text-to-image model from idiogram, now available for free to all users, marking a significant update in AI image generation.
  • 📈 Idiogram 2.0 stands out for its unique model and ability to incorporate text into images, though it lacks some advanced features like control nets and IP adapters.
  • 🎨 The video tests idiogram 2.0 against other AI models in categories such as human realism, landscape, text incorporation, and absurd images, showcasing the model's capabilities.
  • 🆚 In comparison, Midjourney, feeling the competitive pressure, opened up free trials and web experience to attract users, offering roughly 25 free images to test their platform.
  • 📉 Despite Midjourney's advancements, it falls short in text incorporation and prompt adherence compared to other models like idiogram and Dolly 3.
  • 🆓 Other models like Mystic from Freepick and Phoenix from Leonardo also offer free or limited free usage, contributing to the competitive landscape of AI image generation.
  • 💸 The video discusses the pricing models of various AI image generators, highlighting the different strategies companies use to attract users, from free trials to daily credit systems.
  • 🏆 The conclusion emphasizes the convergence of AI image generation models in terms of quality and features, with each model having its strengths in areas like realism, text incorporation, and prompt adherence.

Q & A

  • What recent development in AI image generation has been noted in the transcript?

    -The recent development noted is the surge in innovation with AI image generation, particularly with the release of new models like Idiogram 2.0 and the opening of free trials for Midjourney, indicating increased competition in the field.

  • Why is Idiogram 2.0 significant in the context of AI image generation?

    -Idiogram 2.0 is significant because it is a highly advanced text-to-image model that is now available for free to all users, offering a strong alternative to other AI image generators.

  • What are some of the limitations of Idiogram 2.0 mentioned in the transcript?

    -While Idiogram 2.0 is praised for its capabilities, it is noted that since it's not an open model, it lacks features like control nets, LURAs, IP adapters, inpainting, and outpainting that are available with other models.

  • What is the daily limit for free image generation with Idiogram 2.0?

    -Users can generate about 40 images per day for free with Idiogram 2.0, as it provides 10 credits per day and each credit generates four images.

  • How does the transcript suggest Midjourney is responding to competition in AI image generation?

    -The transcript suggests that Midjourney is responding to competition by opening up its web experience to everyone and temporarily offering free trials, allowing users to generate a limited number of images without cost.

  • What are the four areas tested in the AI image generation models as per the transcript?

    -The four areas tested are human realism, landscape and scenery, incorporating text into images, and the creation of weird and absurd images.

  • What is the free trial limit for Midjourney as mentioned in the transcript?

    -The free trial limit for Midjourney is 25 images in total, after which users have to pay to continue using the platform.

  • How does the transcript describe the performance of different AI image generation models in terms of prompt adherence?

    -The transcript describes Dolly 3 as the best at prompt adherence, ensuring all elements from a complex prompt are included in the generated image.

  • Which AI image generation model is highlighted as excelling in incorporating text into images?

    -Idiogram is highlighted for excelling in incorporating text into images, with its unique model that stands out in this capability.

  • What is the author's personal opinion on Leonardo's Phoenix model as an adviser?

    -The author, as an adviser to Leonardo, expresses a personal bias towards the Phoenix model, appreciating its high-quality image generation and particularly its aesthetic and color contrast.

Outlines

00:00

🌐 AI Image Generation Advances

The paragraph discusses the recent surge in AI image generation innovation, particularly mentioning the capabilities of the AI model 'Grock 2'. It notes the realistic image generation but also its limitations, such as the exclusion of adult content. The speaker highlights their own extensive use of the 'Flux' model from Black Forest Labs in their recent videos, showcasing its ability to create super realistic images and train with custom faces. The paragraph also introduces 'Idiogram 2.0', a new text-to-image model that excels at incorporating text into images and is now available for free, contrasting it with other models that offer more control due to their open nature.

05:00

🆓 Free AI Image Generation Models

This paragraph focuses on the accessibility of AI image generation models, noting that 'Idiogram 2.0' allows 10 credits per day for free, which translates to about 40 free images daily, with a paywall for additional usage. It also discusses 'Mid Journey', another AI model, which has opened up its web experience and提供免费 trials, albeit with a limit of 25 free images. The speaker speculates that the increased competition in the AI image generation space might be prompting companies like Mid Journey to offer free trials to attract users.

10:02

🎨 Testing AI Image Generation Models

The speaker details their testing process for various AI image generation models, including 'Idiogram', 'Mid Journey', and 'Free Pick Mystic'. They use four different prompts to evaluate the models on human realism, landscape scenery, text incorporation, and the creation of weird and absurd images. The results are analyzed for each model, with 'Idiogram' showing strong performance in all categories, 'Mid Journey' excelling in realism but struggling with text, and 'Free Pick Mystic' demonstrating good image generation capabilities.

15:03

📊 Comparative Analysis of AI Models

This paragraph presents a comparative analysis of different AI image generation models based on the speaker's tests. It mentions 'Leonardo Phoenix' as a high-performing model, especially in terms of color and detail. The speaker also provides a visual comparison tool in Figma, allowing viewers to zoom in and assess the quality of the generated images. The paragraph discusses the convergence of capabilities among various models, with each having its strengths in different areas such as prompt adherence, realism, and text incorporation.

20:04

💸 Pricing and Availability of AI Models

The final paragraph summarizes the pricing and availability of the AI image generation models discussed. It outlines the free tiers and limitations of each model, such as 'Idiogram 2.0' offering 10 free images per day and 'Mid Journey' providing a one-time 25-image free trial. The speaker also mentions the free availability of some models within specific platforms like Instagram and WhatsApp for 'Meta's Emu'. The paragraph concludes by emphasizing the benefits of competition in the AI space, which offers users a wide range of options to suit their needs.

Mindmap

Keywords

💡AI image generation

AI image generation refers to the use of artificial intelligence algorithms to create images based on textual descriptions or other data inputs. In the context of the video, AI image generation is the central theme, with various models being discussed for their ability to produce realistic and diverse images. The video explores how these AI models have advanced, with some being capable of generating uncensored and highly realistic images, while others specialize in incorporating text or maintaining prompt adherence.

💡Grock 2

Grock 2 is mentioned as a platform that utilizes AI to generate realistic images, with the capability to produce a wide range of content except for adult material. The video suggests that Grock 2 is using the Flux model from Black Forest Labs, indicating the underlying technology that powers its image generation capabilities. Grock 2 serves as an example of the current state of AI image generation and the type of innovation being discussed.

💡Flux model

The Flux model is an AI model used by Grock 2 for generating images, as mentioned in the video. It is part of the broader discussion on the different AI models and their capabilities. Flux is highlighted as a model that is being heavily utilized by the presenter, showcasing its effectiveness in producing high-quality images, and is compared with other models throughout the video.

💡Idiogram 2.0

Idiogram 2.0 is a text-to-image model introduced in the video as a significant advancement in AI image generation. It is noted for its ability to incorporate text into images effectively, which sets it apart from other models. The video discusses how Idiogram 2.0 is now available for free to all users, making it an appealing option for those looking to generate images with text elements.

💡Mid Journey

Mid Journey is an AI image generation platform that is mentioned in the video as responding to competition by offering free trials. The video suggests that Mid Journey may be feeling pressure from other free or less expensive AI image generation models and is attempting to make its product more appealing by allowing users to test it without cost. The platform's images are also compared with those from other models for various criteria.

💡Prompt adherence

Prompt adherence refers to how well an AI image generation model can accurately include all elements specified in a textual prompt into the generated image. The video discusses this concept as a key metric for evaluating AI models, with some models like Dolly 3 being praised for their ability to include multiple elements from complex prompts into the final image.

💡Realism

Realism, in the context of the video, pertains to the ability of AI models to generate images that closely resemble real-world visuals. The video compares different AI models based on their realism, with some models like Flux 1.0 and Mid Journey 6.1 being noted for their high level of realism in the images they produce.

💡Text incorporation

Text incorporation is the ability of an AI model to include textual elements within the generated image as per the user's prompt. Idiogram 2.0 is highlighted in the video for its prowess in this area, being able to integrate text seamlessly into the images it creates, which is a valuable feature for users looking to create images with specific text.

💡Free trials

Free trials are a strategy used by AI image generation platforms, like Mid Journey, to attract users by allowing them to test the platform's capabilities without cost. The video discusses how Mid Journey has opened up free trials as a response to competition, providing users with a limited number of free images to evaluate the service before deciding to subscribe.

💡Aesthetics

Aesthetics in the context of the video refers to the visual appeal and artistic quality of the images generated by AI models. Different models are evaluated for their aesthetics, with some, like Leonardo's Phoenix, being praised for their color contrasts and visual appeal. Aesthetics are subjective, and the video suggests that users may have different preferences for which AI model produces the most pleasing images.

Highlights

Midjourney has made its AI image generation free again, possibly in response to competition.

Recent AI image generation innovations have been driven by models like Grokk 2 and Flux from Black Forest Labs.

Idiogram 2.0, a new model from Idiogram, offers advanced text-to-image capabilities for free.

Idiogram 2.0 is unique for its ability to incorporate text into images, a feature that stands out among other models.

A comparison of AI image generators is conducted using four different prompts to test various capabilities.

Human realism, landscape scenery, text incorporation, and absurd image generation are the four key areas tested.

Idiogram 2.0 produces impressive results in human realism and landscape scenery, but has some noise in the images.

Midjourney's free trial allows for 25 images, a strategic move amidst competitive market offerings.

Midjourney's text incorporation in images is not as strong as other models like Idiogram 2.0.

Freepick's Mystic model shows potential but is still in Alpha, with limits on daily AI image generation.

Leonardo's Phoenix model generates high-quality images, especially in color contrast and aesthetics.

Dolly 3 excels in prompt adherence, ensuring all elements of a complex prompt are included in the image.

The competition in AI image generation is driving innovation and offering users a variety of free and high-quality options.

A detailed comparison chart is provided to help users decide which AI image generator best fits their needs.

The video concludes that the landscape of AI image generation is competitive, with each model having its strengths.

The host of the video is an adviser to Leonardo, providing a potential bias towards their products.