Images
https://www.youtube.com/@NataliaKalinska
Canva Tutorials
https://www.123rf.com/
PhotoPea - Online photo editor
Shakker - image generation, image improvement
- cartoon, 3d Avatar, photograph
- png, gif, jpg
- SVG, raster, vector
- layers, background, foreground
- color, fill, gradient
- shape, distortion, skew
- orientation, direction, mirror
- image size, pixelation, quality
- selection tool
- undo, step backward
- file size, compression
PicLumen - image generator
Canva - 500 generations per month, 4 images on each generation
Leonardo.ai
Fooocus, Google Labs
Flux
Adobe Background Remover
https://docs.midjourney.com/docs/settings-and-presets
1. Canva, Photoshop
2. face swap
3. consistent characters
4. backgrounds
5. picture quality
6. image generation
7. Discord server
8. MidJouney vs Leonardo
9. Teaching Channels
SVG (Scalable Vector Graphics) is a vector-based image format. SVG images are made up of paths defined by mathematical equations. This means they can be scaled to any size without losing quality, making them ideal for responsive web design, icons, logos, illustrations, and other graphics that need to look sharp on any screen.
SVG files are also text-based, meaning you can view and edit them with a text editor. The SVG format supports interactivity and animation, making it versatile for various web applications. Additionally, because they are XML-based, SVGs can be searched, indexed, compressed, and scripted.
Raster images, such as JPEGs or PNGs, are made up of pixels
https://www.youtube.com/@TokenizedAI/videos
The Zinnny Studio - digital products, animation, kids Books
Glibatree - offering a trained 'Glibatree Art Designer', can access through ChatGPT 4
Monzon Media
Jump Into AI
AI Edge Mastery
All Your Tech
Singularity Tutorials
AI Influencer
Leonardo AI
Bob Doyle Media
Atomic Gains
Image Generators
Fooocus - Google Co-Labs
Leonardo AI - generate free images
Playground AI
Runway ML
SeaArt.ai - uncensored tools
CapCut
ChatGPT PLUS - need paid plan to use Dall-E 3
Civit AI
https://tensor.art/
https://www.picsi.ai/ - face swap, images, gif animations, videos? daily limit of 50 swaps.
-----
Canva - uses Stability.ai
Canva Magic Studio
Can use Andover.edu or UC Berkeley to get .edu email, and can sign-up as a student or educator, and get canva free or lower cost.
https://www.youtube.com/@metricsmule/videos
------
Unstable Diffusion - X-rated
Bing Image Creator - needs Microsoft hotmail signin
-------------
Ideogram - can add text spelled correctly to an image, for logo, T-shirt design
DreamStudio - often blurs sensual content
Lime Wire - use the Blue Willow Model, limited free usage
GenCraft - can use trained models if upgrade
Google Gemini - temporarily can't create images of people
Imaging Projects
1. Stable, consistent characters for kids book illustration
2. Initial characters for training consistnt character models
3. Base for character animation
4. Iconic character for our series: Miss Kitty, Peppa Pig, Miss Bimbo
Image Prompts
https://openart.ai/community/AqkSeee40nBncNncCO6a
https://huggingface.co/Gustavosta - prompt generators
Study the different modules, add-ons, tools.
style, backgrounds, editing, faces, emotions, lip synching
'Please create an image'
- Description
- Character
- Pose
- Emotion
- Fashion
- Setting
- Style - the style of the photography or art
- Artist (paint, photographer)
- Lighting
- Camera Angle
Consistent Characters
https://ailemonacademy.ck.page/
Consistent Characters
Fooocus, Google Co-labs
Fooocus - consistent faces
Face Swap
Image Input (prompt)
Text Prompt Engineering, word order, girl's name, repetition
Fixed Seed
- Leonardo
in Midjourney, can press the emoji-like button, to emphasize a 'good job' ie, prioritize that image. Also, can press envelope icon, revealing seed. finally, can find file location of image, and inlude that address at the beginning of the prompt.
https://www.youtube.com/@iammiameow/videos - consistent characters via bot-GPT creation in ChatGPT 4.
Characters, ArtFlow
https://www.youtube.com/watch?v=UdkQX88clIM
https://www.youtube.com/watch?v=Sc2f2oTaR7U
https://www.youtube.com/@DigitalSuccessAI/videos
'Consistent Character GPT,' can access through ChatGPT 4
Character Consistency
- Prompt Detail
- Face Swap
- Custom GPTs
- Software
- Sprite Sheets
- Training
https://intercom.help/leonardo-ai/en/articles/8584503-creating-consistent-characters
https://characteraigenerator.com/
Use generated images as sprite sheets, for animation.
Image Editing
https://www.remove.bg/
PNG with transparent background
- Small Size (.jpg)
- Raster Image (.png)
- Vector Image (.eps)
Upscale
In-Painting
Local Installation
Stable Diffusion dowload, install on our PC.
https://platform.stability.ai/
https://www.midjourney.com/ - excellent AI-generated images, but high pricing. Even with a paid plan, you will have to carefully balance your allocated hours. Midjourney works exclusively through the chat app Discord.
Discord
Hugging Face
- OpenDevin (software programming)
- Grok (LLM - AGI)
----------
Google Labs
Fooocus - Stable Diffusion
https://colab.research.google.com/drive/1Ab5bnDxRh69UMV8UMkz_rGWRkO9-vSsd
- rename fooocus and data folders -
https://colab.research.google.com/github/lllyasviel/Fooocus/blob/main/fooocus_colab.ipynb
Image FX by Google:
Not yet available in Thailand, can try free VPN services:
https://aitestkitchen.withgoogle.com/tools/image-fx
----------
https://huggingface.co/
'Anything V3' is a special-purpose model trained to produce high-quality anime-style images. You can use 'danbooru tags' (like 1girl, white hair) in the text prompt.
Microsoft
Microsoft (OpenAI sponsor)
VALL-E (text to speech with natural accents)
CoPilot Website
Designer, by Miscrosoft - needs Microsoft hotmail signin
Bing Image Creator - needs Microsoft hotmail signin
Bing Image Creator: Due to Microsoft’s partnership with OpenAI, you can use the DALL-E 3 image generator via Bing for free. You get 100 boost credits to start with and unlimited slower generations thereafter.
ClipChamp needs Chrome or Edge browser, could be good for txt to speech