How To - Nightcafe Studio - Create A Basic Image

Ai Text To Image
22 Aug 202206:10

TLDRIn this introductory tutorial by Matt Carter, viewers are taken through the basics of creating an image using NightCafe's four models, focusing on the first three: Coherent, Artistic, and Stable Diffusion. Carter demonstrates the process with a simple prompt, showcasing the differences in output between the models and highlighting the potential of each. The video serves as a foundation for newcomers, with more complex tutorials to follow, encouraging viewers to stay tuned for updates and explore NightCafe's capabilities further.


  • 📌 Matt Carter introduces a series of tutorials for NightCafe, covering basics to advanced topics.
  • 🎨 The video series includes instructions on using NightCafe's four models, starting with the basics.
  • 🏠 Video one demonstrates how to create a basic image using all three (now four) of NightCafe's models.
  • 📝 NightCafe offers models like Coherent, Stable, Artistic, each with its own approach to image generation.
  • 🔍 Coherent aims for precision and closely follows the prompt, Artistic focuses on a more creative interpretation.
  • 🤔 Stable Diffusion combines the strengths of Coherent and Artistic, offering a balance between accuracy and creativity.
  • 🌐 The video provides a prompt example: 'a house on a riverbank, blue sky, white clouds, and shining sun'.
  • 🎨 The process involves creating an image with minimal adjustments, using the same prompt across different models for comparison.
  • 🚀 Each model generates images with unique seeds, leading to different outcomes.
  • 📸 The video showcases the results, highlighting how each model interprets and represents the prompt.
  • 📈 The tutorial is aimed at new users and serves as a foundation for understanding NightCafe's capabilities.
  • 🔗 Matt Carter encourages viewers to subscribe for more tutorials and offers a discount code for NightCafe Pro subscriptions.

Q & A

  • Who is the speaker in the video transcript?

    -The speaker in the video transcript is Matt Carter, the creator of the tutorials for NightCafe.

  • What is the purpose of the video?

    -The purpose of the video is to provide a tutorial on how to create a basic image using all four of NightCafe's models, starting from the very basics.

  • What are the four models Matt Carter mentions in the video?

    -The four models mentioned are Coherent, Stable, Artistic, and Stable Diffusion.

  • How does Matt Carter describe the Coherent model?

    -The Coherent model is described as trying to get as close to the prompt as possible by being pretty strict.

  • How does the Artistic model differ from the Coherent model?

    -The Artistic model also aims to get close to the prompt but does so in an artistic fashion, allowing for more creative interpretation.

  • What is the main advantage of the Stable Diffusion model?

    -The Stable Diffusion model is a combination of both Coherent and Artistic, performing better at both in most circumstances.

  • What is the basic prompt Matt Carter uses for the demonstration?

    -The basic prompt used for the demonstration is 'a house on a riverbank, the sky is blue, the clouds are white, and the sun is shining'.

  • How long does it typically take for the models to create an image?

    -The time it takes for the models to create an image is not explicitly stated, but the Stable Diffusion model in the demonstration appears to finish quickly.

  • What does Matt Carter suggest viewers do after watching this video?

    -Matt Carter suggests that viewers watch all the videos in order to follow the progression and learn more complex aspects of using NightCafe.

  • How can one get a discount on NightCafe's pro subscription?

    -A discount code is available on the website and YouTube that provides a 5% discount on NightCafe's pro subscription.

  • What is the significance of the seed number in the video?

    -The seed number is significant because it contributes to the uniqueness of the generated image. Different seed numbers will result in different images even with the same prompt.



🎨 Introduction to NightCafe Video Tutorials

Matt Carter introduces the NightCafe video tutorials, explaining that the series covers content from basic to advanced levels. The current video is the first in the series, focusing on creating a basic image using NightCafe's models, which now include stable diffusion. Matt emphasizes that the video is being made before the release of the stable diffusion feature and that the series will progress in complexity. He provides a brief overview of the different models: Coherent, Artistic, and Stable Diffusion, and how they handle prompts differently. Matt then demonstrates the process of creating an image using a simple prompt, showing the results from each model and noting the differences in their outputs.


📺 Quick Guide to Creating Basic Images

Matt acknowledges the common questions from new users about creating basic images on NightCafe and assures that this video serves as a good starting point. He emphasizes the importance of watching the entire series in order to follow the progression of tutorials. Matt encourages viewers to subscribe for more upcoming content and mentions a discount code available on the website and YouTube for a Pro subscription to NightCafe. He concludes the video by thanking the viewers and looking forward to the next tutorial.



💡Matt Carter

Matt Carter is the presenter of the video tutorials for NightCafe, a platform for creating images using AI models. He introduces himself at the beginning of the video, setting the stage for the tutorial series.


NightCafe is an AI-based platform that allows users to create images using various models. It is the central focus of the video, where Matt Carter demonstrates how to use it to generate images based on prompts.

💡Stable Diffusion

Stable Diffusion is one of the AI models available on NightCafe. It aims to combine the best aspects of the other two models, Coherent and Artistic, to generate images that are both accurate to the prompt and artistically rendered.


Coherent is an AI model in NightCafe that focuses on generating images that closely match the user's prompt, aiming for precision and accuracy in the depiction.


The Artistic model in NightCafe is designed to create images that adhere to the user's prompt but with a more creative and artistic interpretation, allowing for a less rigid and more expressive outcome.


A prompt is a text input provided by the user to guide the AI in creating an image. It serves as the basis for the image's content and style, and the AI models interpret it to generate the final image.


In the context of the video, 'create' refers to the action of generating an image using the NightCafe platform and the chosen AI model. It is the primary function that users perform to produce visual content.

💡Image Collection

The Image Collection is a feature or section within the NightCafe platform where users can view and organize the images they have generated.


Discord is a communication platform where the NightCafe community likely interacts, asks questions, and receives support. It is mentioned as a place where many users seek help on creating basic images.

💡Pro Subscription

A Pro Subscription to NightCafe is a premium membership that offers additional features and benefits to users, such as higher-quality image generation or faster processing times.

💡Tutorial Series

The Tutorial Series refers to the collection of videos Matt Carter is creating to guide users through the process of using NightCafe. The series starts with the basics and progresses to more advanced topics.


Matt Carter introduces his video tutorials for NightCafe, covering both basic and advanced topics.

The video series starts with the basics of creating an image using NightCafe's models.

NightCafe now includes stable diffusion in its models.

The tutorial demonstrates creating an image using all four of NightCafe's models.

Coherent model aims for accuracy and strict adherence to the prompt.

Artistic model interprets the prompt in a more creative and artistic manner.

Stable diffusion combines the strengths of both Coherent and Artistic models.

The video provides a basic prompt to demonstrate the models' capabilities: 'a house on a riverbank, with a blue sky, white clouds, and shining sun'.

The process of creating an image is shown step by step, starting with the Coherent model.

The Artistic model's creation is shown, highlighting its strict adherence to the prompt.

The Stable Diffusion model's output is discussed, noting the missing river element.

The video emphasizes the importance of watching all tutorials for a comprehensive understanding.

Matt Carter encourages viewers to subscribe for ongoing video content.

A promotional code for a 5% discount on NightCafe's Pro subscription is mentioned.

The video serves as a baseline for beginners and is meant to be followed by more detailed tutorials.