I Made The Same Image In Every AI Program Ever

I Made The Same Image In Every AI Program Ever

by Matt Wolfe

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Matt Wolfe 👥 1.0M 📅 July 5, 2023 ⏱ 26 min 👁 90K 📄 review 🧭 2026-08-28
Available in: English (current) Français

Keywords

AI artimage generationMidjourneyStable DiffusionDALL-E

Summary

In this video, Matt Wolfe tests a wide range of AI image generators using the same prompt: ‘A blonde woman on an urban city sidewalk with skyscrapers in the background on a beautiful, sunny day.’ He starts with Automatic1111 and Stable Diffusion 1.5, noting its complexity and the need for custom models. He then tests Midjourney, which produces impressive results with default settings, and Adobe Firefly, which offers different styles. Stable Diffusion XL shows improvement over 1.5. DALL-E 2 and Bing Image Creator produce less detailed images. DeepFloyd is noted for its text generation capability but poor human rendering. Scenario is tailored for game assets. BlueWillow, NightCafe, Lexica, Craiyon, Canva, Playground AI, Dreamlike Art, and Leonardo are also tested, each with varying results. The creator highlights that most tools use underlying models like Stable Diffusion, DALL-E, or Firefly, with Midjourney being proprietary. He concludes by comparing the best images and offering his personal preferences, noting that while better results are possible with prompt engineering, this test uses a simple prompt to compare default outputs.

174 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a valuable comparative overview of AI image generators, offering practical insights into their default performance with a simple prompt. The argumentation is clear and structured, with the creator explaining the underlying models and the limitations of each tool. He acknowledges that results can be improved with prompt engineering, but his goal is to show baseline performance. The disclosure of his advisory role with Leonardo adds transparency. The comparison is useful for viewers deciding which tool to try, though the single-prompt methodology limits generalizability.

Scientific Rigor, Source Quality, Title Accuracy

The video demonstrates scientific rigor by using a consistent prompt across all tools and clearly explaining the methodology. The creator cites the tools’ websites in the description, providing direct sources for each generator. He also mentions FutureTools.io as a resource for discovering AI tools. The title accurately reflects the content, and the video is well-structured with chapters. The creator’s disclosure of his advisory role with Leonardo is a positive sign of transparency. However, the video does not delve into technical details of the models, and the results are based on a single prompt, which may not represent each tool’s full capabilities.

202 words

Title / Content Match

The title accurately reflects the content: the creator tests the same image prompt across numerous AI programs, providing a comprehensive overview.

Quality & Reliability

7/10

The video is a practical comparison of AI image generators using a consistent prompt. The creator discloses an advisory role with one tool, which is transparent. The methodology is clear but limited to a single prompt and default settings, and the creator acknowledges that results can vary with different prompts and settings. The information is current as of mid-2023 and may be outdated.

Chapters

Cited Sources

  • Leonardo AI — AI image generator tested in the video.
  • ClipDrop - Stable Diffusion — Used to test Stable Diffusion XL.
  • NightCafe Creator — AI art generator tested in the video.
  • Dreamlike.art — AI art generator tested in the video.
  • Adobe Firefly — AI image generator tested in the video.
  • FutureTools — Resource for discovering AI tools, mentioned in the video.
  • FutureTools Discord — Community link from the description.
  • InstantArt — AI art generator mentioned in the video.
  • OpenAI Labs (DALL-E 2) — Used to test DALL-E 2.
  • Lexica — AI art generator tested in the video.
  • Matt Wolfe's Blog — Personal blog of the creator.
  • Mubert — Music generator used for the outro.
  • Playground AI — AI art generator tested in the video.
  • Replicate - DeepFloyd IF — Used to test DeepFloyd.
  • Scenario — AI art generator for game assets, tested in the video.
  • Bing Image Creator — AI image generator tested in the video.
  • BlueWillow — AI art generator tested in the video.
  • Canva — Design platform with built-in AI image generator, tested in the video.
  • Craiyon — AI art generator tested in the video.
  • FutureTools Newsletter — Newsletter link from the description.

Concurring Sources

  • FutureTools — The creator's own resource for AI tools, mentioned in the video.

Contribution & Novelties

This video provides a practical, side-by-side comparison of numerous AI image generators using a consistent prompt, offering viewers a clear overview of the current landscape in mid-2023. It highlights that most tools rely on a few underlying models (Stable Diffusion, DALL-E, Firefly), which is a valuable insight for users. The creator’s personal preferences and tips add practical value.

Pour aller plus loin :

98 words

Radar Profile

The radar profile shows high scores in quantity of information and fiabilité, reflecting the comprehensive coverage and transparent methodology. The technical level is moderate, as the video is accessible to a general audience. The overall quality is strong, with a slight dip in technical depth.

Reliability 7/10

💬 Positif. Sur les 30 commentaires analysés, la majorité exprime de l'appréciation pour la comparaison utile et la transparence, avec quelques suggestions d'amélioration comme l'utilisation de modèles personnalisés pour Stable Diffusion.