How To - Nightcafe Studio - How To Use Start Images (Basics)

Ai Text To Image
22 Aug 202210:45

TLDRIn this video, Matt Carter introduces viewers to the basics of using start images with NightCafe, a creative platform. He demonstrates how to enhance a personal photo or a found image using different modes, such as Coherent and Artistic, without the need for advanced drawing skills. Carter also teases an upcoming video on Stable Diffusion and encourages viewers to experiment with the tools to achieve better results. He invites feedback and interaction on Discord and offers a glimpse into the creative process, highlighting the potential and limitations of AI in interpreting detailed versus minimally detailed images.


  • 🎨 The video is part of a series by Matt Carter for NightCafe, focusing on using start images at a novice level.
  • 🖼️ The content covers how to use both self-made and found images as start images in creative processes.
  • 🚀 At the time of the video, Stable Diffusion has not yet been released, which would handle start images differently.
  • 🌲 The tutorial begins with using a photo of a road with trees and sunlight, aiming to enhance it while keeping it recognizable.
  • 📸 The video emphasizes the importance of starting with advanced options and selecting a suitable start image.
  • ✍️ A prompt is written to describe the scene closely, to guide the AI in creating a coherent image.
  • 🎨 Two modes are demonstrated: Coherent and Artistic, each offering different styles of image manipulation.
  • 🖌️ Matt Carter attempts to 'draw' the scene described, highlighting the difference between detailed and minimal input.
  • 🤖 The AI's interpretation of the hand-drawn input is compared to the professional photograph, showcasing its capabilities.
  • 🔄 The process involves duplicating the start image and changing settings to explore different outcomes.
  • 📢 The video ends with an invitation for feedback and further discussion on Discord, as well as mentions of discount codes for NightCafe Pro accounts.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is how to use start images in NightCafe, including both self-made images and found photos or pictures.

  • What is the intended audience for this video?

    -The video is aimed at novice users who are new to using start images in NightCafe.

  • What software has not been released at the time of the video but is mentioned by the speaker?

    -Stable diffusion software had not been released at the time of the video.

  • What are the three modes or options discussed in the video for using images?

    -The three modes discussed are Coherent, Artistic, and Style Transfer.

  • How does the speaker describe their artistic abilities?

    -The speaker describes themselves as the worst artist in the face of the earth.

  • What elements are included in the prompt example given by the speaker?

    -The prompt example includes a road moving off into the distance, trees on either side, and sunlight shining through the trees onto the road.

  • What does the speaker suggest about the complexity of the prompt?

    -The speaker suggests that the prompt does not have to be complicated and can be as simple as describing the scene with basic elements.

  • What is the outcome of the speaker's attempt to draw the image by hand?

    -The speaker's attempt to draw the image by hand results in a walking disaster, but it still contains the elements they were aiming for.

  • How does the speaker describe the results of using a highly detailed professional photograph versus a hand-drawn, minimal-detail image?

    -The speaker suggests that the AI interprets the highly detailed professional photograph and the hand-drawn, minimal-detail image differently, and this difference is something they aim to explore.

  • What does the speaker encourage viewers to do after watching the video?

    -The speaker encourages viewers to experiment with the techniques shown, check the video description for discount codes for NightCafe Pro accounts, and reach out on Discord to provide feedback or suggestions for future content.



🎨 Introduction to Start Images in NightCafe

Matt Carter welcomes viewers to a video series about NightCafe, focusing on the use of start images. He explains that the video is aimed at novices and will be brief, covering how to use both self-made and found images as start images. He mentions that stable diffusion is not yet available but plans to cover it in a future video. The video begins with a demonstration of using a photo as a start image, emphasizing the simplicity of the process.


🖌️ Exploring Artistic and Coherent Image Manipulation

Matt Carter continues by discussing the manipulation of images using NightCafe's artistic and coherent settings. He explains that these settings alter the image based on a preset style or attempt to maintain the original image's coherence. Matt demonstrates this by creating a prompt based on a photo he has, describing a road with trees and sunlight. He emphasizes the importance of keeping the prompt simple for beginners and shows the results of both artistic and coherent manipulations.


🤹‍♂️ Drawing and AI Interpretation

In the final segment, Matt Carter attempts to draw the photo he used earlier, highlighting the difference between a detailed professional image and a hand-drawn, minimalist interpretation. He demonstrates how the AI interprets the simple drawing and compares the results with the previous, more detailed image manipulation. Matt encourages viewers to experiment with different settings and to share their experiences or feedback on Discord. He concludes by directing viewers to the video description for discount codes and invites further interaction on the platform.



💡Start Images

Start images refer to the initial images used as a reference or inspiration for AI-generated art. In the context of the video, they are essential for setting the基调 for the AI to create a piece of art that aligns with the user's vision. The video discusses using both self-made and found images as start images to influence the output of AI art generation platforms like NightCafe.

💡Stable Diffusion

Stable Diffusion is a term mentioned in the script, likely referring to a specific AI model or technique used for generating images. Although not released at the time of the video, it is implied that this model does not handle start images, suggesting that it operates differently from the other AI art generation methods discussed.


In the context of the video, 'Coherent' refers to an AI art generation mode that creates images which are more logically consistent and closely aligned with the start image. It is presented as an option for users who want the AI to produce a more recognizable and less abstract version of the input image.


The term 'Artistic' in the video relates to an AI art generation mode that takes a more creative and interpretative approach to the start image, resulting in a more stylized and less literal representation. This mode is for users who are looking for a more abstract or artistically manipulated version of their input image.

💡Style Transfer

Style transfer is a technique mentioned in the script that involves taking an image and applying the visual style of one image to another, resulting in a new image that combines the content of one image with the artistic style of another. It is a method used in AI art generation to create unique and visually appealing results.

💡Advanced Options

Advanced options in the context of the video refer to the additional settings and features available in AI art generation platforms that allow users to fine-tune and customize their creations. These options provide more control over the output, enabling users to achieve specific effects or styles.


A prompt in the video is a description or a set of instructions provided by the user to guide the AI in generating the desired artwork. It is a textual input that helps the AI understand the kind of image the user wants to create, based on the start image.


Discord is a communication platform mentioned in the video where users can interact with the creator and other community members. It is used as a channel for feedback, discussions, and sharing of experiences related to the content of the video, such as AI art generation.

💡NightCafe Pro Accounts

NightCafe Pro Accounts are premium memberships offered by NightCafe, an AI art generation platform. These accounts likely come with additional features, capabilities, or benefits for users who want to explore AI art creation more deeply. The video encourages viewers to check the video description for discount codes that can be used to obtain these accounts at a reduced price.

💡AI Interpretation

AI interpretation refers to how artificial intelligence systems understand and process input data, such as images or text, to generate an output. In the context of the video, it relates to how the AI takes the start image and prompt to create a piece of digital art that reflects its 'interpretation' of the given instructions.


Matt Carter introduces a video series for NightCafe, focusing on using start images for novices.

The video aims to be short, sweet, and straight to the point, providing a clear guide on using start images.

Matt discusses using both self-made and found images as start images.

Stable diffusion is not yet released and doesn't handle start images, unlike Coherent and Artistic and Style Transfer.

The video demonstrates using Coherent with a start image, emphasizing the importance of advanced options.

Matt chooses a simple photo of a road with trees and sunlight as the start image for the demonstration.

The prompt written for the Coherent image is kept simple to maintain the essence of the original photo.

Matt explains that one credit creations are used for the demonstration, and no additional settings are adjusted.

The video shows the process of creating an artistic version of the image, with Matt noting the differences in manipulation.

Matt plans to create another video to cover artistic, coherent, and stable diffusion settings in more detail.

A hand-drawn version of the image is attempted to show the AI's interpretation of minimal detail versus a detailed photograph.

Matt acknowledges his lack of artistic skill, emphasizing that the outcome will be interesting regardless of the quality.

The video concludes with Matt encouraging viewers to experiment with start images and to reach out on Discord for feedback or questions.

Discount codes for NightCafe Pro accounts are mentioned, directing viewers to check the video description.

Matt invites viewers to provide feedback on his videos, whether positive or critical, and to engage with the community.