Create Ai Videos with Consistent Characters! - Midjourney + Kling

Tao Prompts
15 Oct 202406:06

TLDRThis video tutorial guides viewers on creating AI videos featuring consistent characters. It begins with using Midjourney to generate reference photos and base images, ensuring detailed prompts for consistency. The process involves injecting characters into scenes, refining images for accuracy, and animating them with AI video tools like Clean AI. The result is a dynamic video showcasing characters Kim and Lisa enjoying their Italian vacation, complete with expressive gestures and interactions.

Takeaways

  • 🖼️ Create AI videos with consistent characters using AI tools like Midjourney and Kling.
  • 🏞️ Start by generating reference photos for characters with detailed prompts, focusing on hairstyle, ethnicity, age, and clothing.
  • 👥 Use the same camera or film type for both characters to maintain consistency.
  • 📸 Generate 'Base images' without characters, then inject the characters into these scenes using the reference photos.
  • 🖌️ Use the editor tool to erase and repaint parts of the image to match the reference photos and fix inconsistencies.
  • 🔍 Look for inconsistencies in the injected characters and make edits to ensure they match the reference photos.
  • 👚 When injecting characters, pay attention to details like body proportions and clothing to maintain realism.
  • 🎬 Use AI video tools like Clean AI to animate the images, creating dynamic motion for the characters.
  • 🗣️ In the AI video settings, adjust sliders to match the prompt's actions and increase the video's adherence to the script.
  • 🎥 Clean AI provides high expressiveness in human videos, with detailed arm gestures, facial expressions, and body language.
  • 🛠️ If consistency is key, consider using other tools like Runway or Luma Video for fewer artifacts and deformities.

Q & A

  • What is the main focus of the video?

    -The video explains how to create AI videos featuring multiple, consistent characters using Midjourney and Kling.

  • What is the first step in generating AI videos with characters?

    -The first step is to generate reference photos for the characters using Midjourney, being detailed in the prompts.

  • Why is it important to specify hairstyle in the prompts?

    -Specifying hairstyle is crucial for achieving consistent results, as AI can generate various hairstyles if not clearly defined.

  • What types of images are referred to as 'Base images'?

    -'Base images' are the initial images into which the characters will be injected, such as a scene of the Coliseum.

  • How do you inject characters into a base image?

    -You erase the parts of the base image where the characters will go and then use the copied image URLs of the reference photos to replace those areas.

  • What should you do if the character injection results are inconsistent?

    -If the results are inconsistent, you should try different character reference photos until you find ones that work better.

  • What AI tool is recommended for animating the images?

    -The video recommends using Clean AI for animating the images due to its dynamic motion capabilities.

  • What adjustments can be made to enhance the video generation?

    -You can adjust settings, such as the relevant slider, to increase the accuracy of how well the video follows the prompt.

  • What is the advantage of using Clean AI over other video tools?

    -Clean AI is noted for its expressiveness, particularly in human motions, making character animations more lifelike.

  • What is the narrative outcome for the characters in the video?

    -The characters, Kim and Lisa, enjoy a delightful vacation in Italy, exploring the city and indulging in local cuisine.

Outlines

00:00

🎨 Creating AI-Generated Vacation Photos

This paragraph details the process of creating AI-generated vacation photos featuring consistent characters. The author begins by using an AI image generator, such as Mid Journey, to create reference photos for the characters, emphasizing the importance of detailed prompts, especially for hairstyles and clothing. The author then describes generating 'base images' by injecting these characters into various settings, such as the Coliseum, using the same prompts and film type. The process involves editing the images to remove inconsistencies and ensuring the characters' attributes match the reference photos. The author also discusses the use of the editor tool to refine the images, such as erasing unwanted details and repainting certain areas, to achieve a more accurate representation of the characters. Finally, the author mentions the importance of upscaling the photos for higher resolution before using an AI video generator to animate the characters.

05:00

🎥 Animating Characters with AI Video

The second paragraph focuses on animating the AI-generated characters using video. The author praises the expressiveness of the AI video tool, Clean AI, for its ability to create dynamic motion and realistic human gestures, facial expressions, and body language. Despite some minor issues like artifacts and deformities, the author finds Clean AI to be superior for bringing characters to life. The paragraph also includes a narrative of the characters' vacation, where they explore Rome, visit the Coliseum, and enjoy a meal at a trattoria, capturing the city's timeless charm. The author concludes by encouraging viewers to watch another video for tips on prompting high-quality human motions in AI video tools.

Mindmap

Keywords

💡AI videos

AI videos refer to videos that are created or enhanced using artificial intelligence. In the context of the video, AI is used to generate images and animate characters, bringing them to life in a virtual setting. The script discusses the process of creating AI videos with consistent characters, which involves using AI tools like Midjourney and Kling to generate and animate images.

💡Midjourney

Midjourney is an AI image generator mentioned in the script. It is used to create multiple photos without characters and then to generate reference photos for the characters. The tool is integral to the process of creating AI videos as it helps in generating the base images and reference photos that are later used to inject characters into various scenes.

💡Consistent characters

Consistent characters are characters that maintain the same appearance and attributes throughout a video or series of images. The video's theme revolves around creating AI videos with multiple characters that look the same in every scene. This is achieved by using detailed prompts and reference photos to ensure that the characters generated by AI tools like Midjourney remain consistent.

💡AI video generator

An AI video generator is a tool that converts still images into moving videos using artificial intelligence. In the script, the AI video generator is used to animate the characters that have been inserted into the base images. The generator helps in creating dynamic motion and bringing the characters to life within the video.

💡Reference photos

Reference photos are images used as a guide or template for generating characters with specific attributes. In the video's narrative, the creator generates reference photos for the characters using Midjourney, focusing on details like hairstyle, ethnicity, age, and clothing. These photos are then used to ensure that the characters injected into the base images are consistent with the desired appearance.

💡Prompts

Prompts are the detailed descriptions or instructions given to AI tools to generate specific images or outcomes. In the context of the video, prompts are crucial for creating consistent characters and scenes. The script mentions using detailed prompts to generate reference photos and base images, specifying details like clothing, hair, and camera type.

💡Kodak portrait 400

Kodak portrait 400 is a type of film mentioned in the script, which is used to give a specific look to the generated images. It is part of the prompt used when generating reference photos and base images, contributing to the aesthetic and consistency of the characters and scenes in the AI videos.

💡Base images

Base images are the initial scenes or settings into which characters are later injected. The script describes generating base images of locations like the Coliseum without characters, and then using these images as a foundation to add the characters using AI tools. This process helps in creating a seamless integration of characters into the scene.

💡Image to video tool

The image to video tool is a feature within the AI video generator that allows for the conversion of still images into animated videos. In the video's context, this tool is used to animate the characters that have been placed into the Coliseum photo, creating a dynamic and engaging video sequence.

💡Expressiveness

Expressiveness refers to the ability of the AI video generator to capture and reproduce human-like movements, facial expressions, and body language. The script highlights the high level of expressiveness achieved with the AI video generator, which is crucial for making the characters appear lifelike and emotionally engaging in the final video.

💡Artifacts and deformities

Artifacts and deformities are imperfections that can occur in AI-generated images or videos, such as blurs or slight distortions. The script mentions that while the AI video generator does an excellent job of bringing characters to life, there can be some artifacts and deformities. These imperfections are part of the challenges in creating high-quality AI videos.

Highlights

Creating AI videos with consistent characters using Midjourney and Kling.

The process involves generating multiple photos without characters and then bringing them to life with AI video.

Tips and tricks are necessary for achieving the best results in character consistency.

Using AI image generator Midjourney to create reference photos for characters.

Importance of detailed prompts, especially for hairstyle, to ensure consistent results.

Including ethnicity, age, and exact clothing details in the prompts for character generation.

The significance of using the same camera or film type for both characters.

Generating base images to inject characters into various scenes.

Specifying each character's details using the same prompts as the reference photos.

Injecting characters into images using the editor tool and reference character photos.

Fixing inconsistencies such as earrings and arm size using the editor tool.

The importance of looking for inconsistencies and fixing them during the character injection process.

Tips for finding character reference photos that will inject properly into the image.

Upscaling photos in Midjourney for the highest resolution before AI video generation.

Animating images using AI video, with Clean AI being used for dynamic motion.

Using the image to video tool with a prompt describing the characters' interaction.

Adjusting settings to increase the accuracy of the video following the prompt.

The superior expressiveness of Cling in human videos compared to other tools.

Addressing artifacts and deformities in AI-generated videos for the sake of consistency.

Comparing Runway, Luma Video, and Cling for character animation consistency.

A demonstration of how the characters' vacation went through Rome, showcasing the effectiveness of the AI video creation process.

Encouragement to watch another video for learning how to prompt for high-quality human motions in Cling.

Casual Browsing

Create Cinematic Ai Videos with Kling Ai! - Ultra Realistic Results

2024-11-03 23:13:00

How to Make Consistent Characters AI Video with PixVerse AI Video Generator

2024-09-29 23:41:02

Create Cinematic AI Videos with Runway Gen-3

2024-09-20 18:11:00

Create Cinematic AI Videos with Runway Gen-2

2024-09-25 21:17:00

Consistent AI Video Characters Are FINALLY Here (FREE FULL Process)

2024-09-30 01:08:00