Text to Image Generation: Use https://gab.ai AI to produce a new image created from scratch, without any pre-existing model or scene. Various text prompts can be used to give instructions for new images based on a given set of training data or variables, such as a specific style or color palette.
What is a text prompt? Text prompts are keywords used to generate a unique set of visual images. A single word, list of words, or sometimes sentences can be used. Quick reference charts (5) below.
Start by asking "What do you want to see?"
Do you want a photo or a painting? What’s the subject of the photo? Person? An animal or perhaps a landscape? What details do you want to add? Try a few of these:
Special Lighting. Soft, ambient, ring light, neon
Environment. Indoor, outdoor, underwater, in space
Color Scheme. Vibrant, dark, pastel, green, gold
Point of view. Front, Overhead, Side, Street view
Background. Solid color, nebula, forest
In a specific art style? 3D render, studio ghibli, movie poster, cartoon drawing, retro Artist? Matisse or Tim Burton? What era? 1950's or 1980's? A specific photo type? Macro, telephoto, fisheye?
Ideas, prompts, resources:
Image prompt workflow Consider: Subject or Object, Setting, Art Style or Artist (Art Nouveau or Matisse), Perspective (angle, porthole, portrait), Solidifier (repetition), Vibe (emotion), Weights (+ or [] ), Adding modifiers like camera lenses or lighting will enhance your image.
Prompt example: "Busy county fair, Americana, in the style of Pieter Bruegel the Elder" "A picture of a brown dog riding a skateboard" "Freeform ferrofluids, beautiful dark chaos"
Prompt generators can be found on line for hints or developing your own ideas. Prompt generators for SDXL or Stable Diffusion may produce better results. Take any prompt and edit parts you'd like to see different by exchanging words, descriptive elements
How do I write a prompt ? Use multiple adjectives and focus on a subject and style keywords that are descriptive. Include the name of the object or scene at the beginning of your prompt. Action words work best.
Use clear and concise language. Write at least 3 to 7 words for the prompt. The masters of art history are fun to explore. Use 'in the style of (your artist)' or 'by____ '
Do the length of text prompts matter? Yes, the more detailed your text prompt is, the more visual references the AI can use to create your rendering. However, the more details you include in your text prompt, the more complex your image is going to be, thus the results may not be exactly what you were expecting.
How many subjects should I use? Usually it's best to use 1 or 2 subjects.
What can I do if the AI is never what I was expecting? It's best to take it one step at a time with text prompts.
First start with the subject and see how it works.
Next, try adding a descriptor and if you notice that the renderings are not very clean or comprehensible, try a different descriptor with a similar meaning.
Do this until the AI image generator comes as close to what results you were looking for as possible.
Prompting Quick Reference ChartsStyle and Composition: Trending on artstation, matte, elegant, illustration, digital paint, epic composition, beautiful, the most beautiful image ever seen Colors: black and white, washed colour, Chromatic Palettes, Monochromatic Palettes, Contrast, Motion Picture Process Lighting: blinding light, candlelight, concert lighting, crepuscular rays, direct sunlight, dusk, Edison bulb, electric arc, fire, fluorescent, glowing, glowing radioactively, glow-stick, lava glow, moonlight, natural lighting, neon lamp, nightclub lighting, nuclear waste glow, quantum dot display, spotlight, strobe, sunlight, ultraviolet, dramatic lighting, dark lighting, soft lighting, gloomy, accent lighting, ambient lighting, backlight and more. Detail: Realistic, unreal engine, octane render, bokeh, vray, houdini render, quixel megascans, depth of field (or dof), arnold render, 8k uhd, raytracing, cgi, lumen reflections, cgsociety, ultra realistic, volumetric fog, overglaze, analog photo, polaroid, 100mm, film photography, dslr, cinema4d, studio quality, grainy Artist's Techniques and Materials Digital art, digital painting, color page, featured on pixiv (for anime/manga), trending on artstation, precise line-art, tarot card, character design, concept art, symmetry, golden ratio, evocative, award winning, shiny, smooth, surreal, divine, celestial, elegant, oil painting, soft, fascinating, fine art Camera Settings
ultra wide-angle, wide-angle, aerial view, massive scale, street level view, landscape, panoramic, bokeh, fisheye, dutch angle, low angle, extreme long-shot, long shot, close-up, extreme close-up, highly detailed, depth of field (or dof), 4k, 8k uhd, ultra realistic, studio quality, octane render
and more..... https://turbofuture.com/graphic-design-video/AI-Image-Generator-From-Text-Stable-Diffusion-Prompts-List#gid=ci02b61935d00026bb&pid=ai-image-generator-from-text-stable-diffusion-prompts-list-MTk1MjA0ODE2MTk5NTU4MzQzCamera prompt keywords:
