Let's Create AI Art & Thumbnails (LIVE)

Let's Create AI Art & Thumbnails (LIVE)

by Matt Wolfe

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Matt Wolfe 👥 1.0M 📅 August 28, 2023 ⏱ 140 min 👁 31K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

AI artthumbnailMidjourneyStable Diffusionworkflow

Summary

In this live stream, Matt Wolfe demonstrates his workflow for creating AI-generated YouTube thumbnails. He starts by using ChatGPT to brainstorm thumbnail concepts, then generates a base image with Midjourney. He uses inpainting in Stable Diffusion (Automatic1111) to swap his face onto the generated character, using a custom-trained model. He then upscales the image with Topaz Photo AI and cleans it up with Photoshop’s generative fill. Finally, he assembles the thumbnail in Canva, using its background remover and text tools. Throughout the stream, he answers viewer questions about AI tools, face-swapping, and his setup. He also mentions using Leonardo AI and discusses the potential of tools like Roop for video face-swapping.

111 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a practical, step-by-step demonstration of a real-world AI art workflow. The value lies in the transparency of the process, including failures and workarounds. The argumentation is based on personal experience and anecdotal evidence, which is appropriate for a tutorial format. The creator does not claim scientific rigor but offers actionable advice for creators.

65 words

Title / Content Match

The title accurately reflects the content: a live session creating AI art and thumbnails.

Quality & Reliability

6/10

The video is a live demonstration of AI image generation workflows, with practical tips and tool recommendations. The creator is experienced in the field, but the content is informal and lacks rigorous scientific verification. Claims about tool effectiveness are based on personal experience rather than systematic testing.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

Concurring Sources

  • FutureTools — The creator's own website, which lists AI tools and is referenced in the video.

Contribution & Novelties

The video offers a practical, real-time demonstration of a complete AI thumbnail creation workflow, combining multiple tools. It provides insights into the creator’s personal techniques, such as using a celebrity lookalike as a prompt keyword and using Canva for final assembly.

Pour aller plus loin :

  • Stable Diffusion — The core model used for inpainting.
  • Midjourney — The AI art generator used for initial images.
  • Generative fill — Photoshop’s AI feature for editing images.

74 words

Radar Profile

The radar profile shows a balanced performance across all dimensions, with slightly higher scores in information quantity and technical level, reflecting the practical nature of the tutorial. The lower score in information quality and reliability is due to the informal, anecdotal style.

Reliability 6/10

💬 Sur les 0 commentaires analysés, aucune tendance n'est disponible.