Generating images is a task AI solved very solidly. You can generate what you want with great specificity, there are vibrant communities with copious amounts of resources to help you piece together your prompt, and there are multiple different models out there, each offering a set of strengths it is particularly good at. Here are some strategies and practices to get you started on this journey.
Elements you can add to your prompt:
- Style modifiers - adjectives which specify a particular style
- Ex.: photorealistic, by greg rutkowski, by christopher nolan, painting, digital painting, concept art, octane render, wide lens, 3D render, cinematic lighting, trending on ArtStation, trending on CGSociety, hyper realist, photo, natural light, film grain
- Quality boosters - terms added to prompts to enhance general attributes of images, not tied to any style
- Ex.: High resolution, 2K, 4K, 8K, clear, good lighting, detailed, extremely detailed, sharp focus, intricate, beautiful, realistic+++, complementary colors, high quality, hyper detailed, masterpiece, best quality, artstation, stunning
- Repetition - repeat the important element of the prompt multiple times
- Ex.: A hairy hairy hairy dog
- Prompt weights - specify in the prompt how much to give emphasis to each word.
- Negative prompts - describing the model what not to do
- Ex.: no disfigured, deformed hands, not blurry, not grainy, not cross-eyed, not undead, not photoshopped, not overexposed, not underexposed, not lowres, no bad anatomy, no bad hands, no extra digits, no fewer digits, no bad digit, no bad ears, no bad eyes, no bad face, not cropped
- Shot types - different camera angles used in photography
- Ex.: Long Shot (main item far away with big background), High-angle Shot (means from top), Low-angle Shot (means shot from below), Bird-eye Shot (shot from top)
Methods for image prompt engineering: