How to Master Composition in MidJourney: Camera Angles, Poses, and Optical Tricks
Expanding your language to describe images helps you prompt better in AI image generation tools like Midjourney.
Blog posts
Create Consistent Characters within ComfyUI
ComfyUI is an AI tool for creating images, videos, and animations. This page talks about the workflow for creating consistent characters for stories.
Broadcast and Media Volume 30, Volume 1 (Ultra-realistic media created by biomorphic AI) (2025-01-30)
This page is in Korean, but you can use Google Translate to read the page. I bookmarked it for the article by Oh Jewook titled "AI-based virtual human-related technology and commercialization." The author used one of my collections of Midjourney images as an example of consistent character images (with citation and permission, of course). Very cool to see my work cited in such a different setting! I never know when I publish a blog post where it might end up being useful to someone else.
Episode 70: Community Hour + InGrasp Demo
Recording of Bryan Jones demonstrating the new InGrasp tool for creating custom character images for scenarios for the ONILP group.
Midjourney Prompts, SREF Codes Library and Examples
Library of Midjourney sref (style) codes. Look for inspiration or copy existing sref codes to generate your own images in that style.
Midjourney --sref codes
A library of sref (style reference) codes for Midjourney. Find a style you like and use it in your prompt to create images in a similar style.
LABS.GOOGLE
Google Labs has an "Experiments" page with a collection of AI tools for a variety of purposes. These are very explicitly experimental and probably not ready for production environments. I also expect many of them will disappear later (this is Google, after all--look at their track record). Still, this looks like a fun site to spend some time exploring what tools can do right now.
35 Midjourney Art Styles to Spark Your Creativity in 2024
Ideas for styles of art to include in your prompts for Midjourney or other AI image generation
AnimateAI
Create animated videos with AI. Start by generating characters, which the site says will be consistent throughout your story. You can turn scripts into storyboards and customize them. Then, create videos in 30-second clips. The voice syncing doesn't look great in their demo videos, but this still might be worth experimenting with. The free plan should be enough to test it out.
Napkin AI - The visual AI for business storytelling
Paste your existing text and generate visuals related to it. Includes icons, diagrams, organizers. Looks like it would work well for presentations to have visuals other than a list of bullet points. Currently free during beta, but will be a paid tool later.
.png?width=350&height=&ar=16:9&mode=crop&format=avif&dpr=2)
Cassidy | The AI Workspace for your team
Want to use LLMs like ChatGPT but need a more secure option? Cassidy is designed for working securely within organizations
Consistent Character AI
A tool for creating character images with the ability to edit expressions, poses, head position, and more. Currently in beta. No free plan, but this has a lot more options than most similar tools.
Free AI photo editor - Edit images online with AI | Freepik
Freepik's online image editor includes some non AI-features like cropping and color adjustments plus some AI features like generating variations and AI backgrounds. Limited generations and downloads on the free plan.
Fugatto AI Audio Generator - Create Unique Sounds and Music with AI
This tool isn't available yet, but it promises the ability to generate sound effects and other audio based on text prompts. One especially interesting feature for my work is the ability to change the emotion for an existing audio sample. Plenty of AI voice over tools can do neutral narration well now, but they're all limited for emotional variability. This could be an improvement.
AI Consistent Character Creator: Poses, Faces & Headshots
Another character image generator
ViddyScribe
AI-generated audio descriptions for videos. This is a way to improve accessibility and make videos more available to blind and low-vision users. Audio descriptions are time-consuming to create manually, which means most orgs skip them. This could potentially be a way to improve accessibility quickly and cheaply.
MagicQuill
MagicQuill is an online image editing tool focused on AI inpainting of existing images. Upload and image and draw the shape of what you want to add or change in the image. The tool guesses what you want and generates a text prompt for you. If it guesses right, you can run it and generate the edited image. If it guesses wrong, you can tweak the prompt. Open source tool with a CC license; you can get the source code and run it on your own server if you want.
Rate My Site: Rate your site in seconds – get instant feedback.
AI-generated feedback on website design. Enter a URL and get a score and feedback on the visual design, layout and clarity, and content. The site provides recommendations for improvements as well. As with all things AI, the recommendations should be viewed with some skepticism, but I found it overall reasonably accurate for the few sites I tested.
If you give FLUX1.1 a prompt like "IMG_1018.CR2" you get back images that are so very hard to tell they're AI.
An odd tip from Twitter/X--use a file name with an extension for raw images as part of the prompt to generate realistic looking photos. I assume this is somehow prompting the model to look for those raw photos, but I wouldn't have thought of trying this.
🤖 Generative AI Resources for All! 🧠
James Finder collected resources for learning about generative AI, including cheat sheets, newsletters, YouTube channels, and courses
StoryArtAI - AI Kid Stories Art Generator
StoryArtAI is an AI image generator designed specifically for creating illustrations for children's books. This probably isn't the most useful tool for workplace training or adult learners, but it might be useful for K12 educators. The tool includes support for creating consistent characters and detailed prompting tips.
Make consistent and editable vector graphics with AI
Brushless is an AI tool focused on creating consistent illustrations, icons, and vector graphics. The tools make it easy to edit the colors, and you can create multiple images in a consistent style. You can get a small number of images as SVGs for free, and for low prices for more downloaded images.
https://leonfurze.com/deepfake-game/
Can you identify which images are generated by AI and which ones are real? Test yourself with these 10 pairs of images. I got 9/10 right, but I think more of these AI images would have fooled me if they weren't in a context where I knew one image in each pair was fake.
DeepBrain AI
Generate avatar videos from text. This tool lets you adjust the gestures for the presentation, as well as generating scripts from links or PowerPoint presentations. These videos definitely hit the uncanny valley and are clearly AI. Plus, how useful are talking head videos even when it's a real person, let alone an AI talking head? However, the free test might be worthwhile if you're interested in experimenting with these sorts of AI video avatars.
Image Upscaler - Upscale Your Photo for Free with AI
AI-powered image editing tools from a small Ukrainian company. Upscale, unblur, cartoonize, remove backgrounds. Use limited free credits per month or use promo code BESTEDITOR to buy credits.
One thing often happens at keynotes and conferences. It surprised me….
Don Clark shares several ways that people with dyslexia are benefiting now from using AI tools. Text-to-Speech, transcription, grammar and spelling assistants, note-taking and summarizing, and other tools can all help people with dyslexia.
3D AI Studio - Create Custom 3D Models with AI
Instead of text to image, this tool lets you generate text to 3D model. You can also generate an image in another tool like Midjourney or Flux and then generate a 3D model from a reference image.
One of the challenges for developing training in VR has always been the development time and cost, including time to develop custom 3D assets. This feels like a step towards making 3D development much more affordable and faster.
AI Art: What Should Fair Compensation Look Like?
Intellectual property is one of the big ethical questions with AI image generation. This article considers conditions for compensating artists for AI images based on specific artists' style and work.
In their research, to see if compensating artists for AI creations was a viable option, the coauthors wanted to see if three basic conditions were met:
– Are artists’ names frequently used in generative AI prompts?
– Do consumers prefer the results of prompts that cite artists’ names?
– Are consumers willing to pay more for an AI-generated product that was created citing some artists’ names?
Crunching the data, they found the same answer to all three questions: yes.
Img2Go.com - Online photo editor and image converter
Multiple image generation and editing tools powered by AI. Upscaling, background removing, face blurring (automatically detecting all the faces in a crowd and blurring them all for privacy), inpainting, image comparison. This site has some basic image editing tools like cropping, rotating, and compressing as well. The basic plan is free, with paid plans for credits for more advanced tools.
Hedra
Image to video creation tool. This might be interesting to experiment with for scenarios. It should be possible to create a character image in Midjourney, and then turn it into a video with this tool. This is probably going to work best with talking head videos, at least right now. h/t Josh Cavalier