Make A Movie with AI: It's Crazy What We Can Do!

Make A Movie with AI: It's Crazy What We Can Do!

by Matt Wolfe

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Matt Wolfe 👥 1.0M 📅 April 25, 2023 ⏱ 24 min 👁 793K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

AI videoRunway Gen-2MidjourneyElevenLabsDaVinci Resolve

Summary

In this tutorial, Matt Wolfe demonstrates how to create a short film entirely using AI tools. He begins by using GPT-4 to generate a script and a detailed shot list for a 60-90 second documentary-style film about an AI robot saving civilization. He then uses Runway Gen-2 to generate video clips from the shot descriptions, supplementing with Midjourney for still images when Gen-2 fails to produce the desired result. For still images, he uses LeiaPix and Kaiber to add animation and cinematic effects. The voiceover is generated with ElevenLabs, and background music is created with Mubert. Finally, he assembles all the assets in DaVinci Resolve, adjusting timing and pacing to match the narration. The video showcases the entire process, including the challenges of consistency and the need for multiple iterations. The final result is a one-minute short film, demonstrating the potential of combining various AI tools for creative projects.

149 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a high practical value by offering a step-by-step workflow that viewers can replicate. The creator demonstrates the strengths and weaknesses of each tool, showing how to combine them to achieve a cohesive result. The argumentation is based on personal experience and is transparent about the effort and iterations required. The video is not a rigorous scientific evaluation but a hands-on demonstration, which is appropriate for its tutorial nature.

Scientific Rigor, Source Quality, Title Accuracy

The creator provides links to all the tools used in the description, which is good practice. However, the video does not cite any scientific sources or studies. The title accurately reflects the content, and the video is well-structured and clear. The creator also mentions the limitations of the tools, such as the closed beta of Gen-2 and the difficulty in achieving consistent characters, which adds to the credibility.

154 words

Title / Content Match

The title accurately reflects the content: the creator demonstrates how to make a movie using AI tools, and the results are indeed impressive for the time.

Quality & Reliability

7/10

The video is a practical tutorial demonstrating a workflow for creating a short film with AI tools. The creator is transparent about the limitations and the iterative process, and provides links to all tools used. However, it is not a scientific study and relies on anecdotal evidence and personal experience.

Key Moments

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

Cited Sources

  • FutureTools — Creator's website curating AI tools
  • ChatGPT — Used to generate script and shot list
  • Runway Gen-2 — Used to generate video clips
  • Midjourney — Used to generate still images
  • LeiaPix — Used to add depth and animation to still images
  • Genmo — Used for time-lapse video generation
  • Kaiber — Used to add cinematic effects to images
  • ElevenLabs — Used to generate voiceover
  • Mubert — Used to generate background music
  • DaVinci Resolve — Used for video editing

Concurring Sources

  • Runway Gen-2 — The tool used for video generation, its capabilities are consistent with the video's demonstration.
  • Midjourney — The tool used for image generation, its capabilities are consistent with the video's demonstration.
  • ElevenLabs — The tool used for voice synthesis, its capabilities are consistent with the video's demonstration.

External References

Contribution & Novelties

The video’s main contribution is a practical, end-to-end workflow for creating a short film using multiple AI tools, demonstrating how to combine text-to-video, text-to-image, voice synthesis, and music generation. It highlights the current limitations and the need for iterative prompting, providing a realistic view of the state of AI filmmaking in 2023.

Pour aller plus loin :

  • Runway ML — The company behind Gen-2, offering AI video generation tools.
  • Midjourney — AI image generation tool used in the video.
  • ElevenLabs — AI voice synthesis platform.
  • DaVinci Resolve — Professional video editing software used for assembly.

95 words

Radar Profile

The radar profile shows high scores in quantity of information and technical level, reflecting the detailed tutorial nature. Quality and reliability are slightly lower due to the lack of scientific rigor and reliance on anecdotal evidence. Overall, the video is informative and practical, but not a scientific reference.

Reliability 7/10

💬 Très positif. Sur les 30 commentaires analysés, la grande majorité exprime admiration et enthousiasme pour la démonstration, avec des remarques sur le potentiel futur de la technologie et des remerciements pour le partage de connaissances.