This post lists the tools you can use to create images through prompting generative AI models.
- Adobe Firefly: https://firefly.adobe.com/generate/image
- Cost: free when you sign in with your CUNY credentials (while this class is running).
- Microsoft Copilot: https://copilot.microsoft.com or https://m365.cloud.microsoft/create
- Cost: free when you sign in with your CUNY credentials (while you are a CUNY student)
- NOTE: you can use this prompt to help you write a more detailed prompt
- I want to create an image. Ask me questions about the subject, setting, and style I want.
- Google Gemini: https://gemini.google.com/app
- Cost: free options when signed in with Google Account.
- Click the Create Image link under the chat before entering a prompt to get more options.
- You need to have a Goole Account to use this properly
- Google AI Studio: https://aistudio.google.com/prompts/new_chat
- Cost: free options when signed in with Google Account.
- Click on the image generation link under the prompt box to access image generation tools.
- The latest models are paid, but the basic Nano Banana model should be available to use for free.
- Hugging Face
- Cost: This site provides some limited free access to models through its Spaces and its ZeroGPU.
- This also allows you more control over the model settings than the tools above. Here are a couple to try:
- FlUX.1-dev by Black Forest Labs: https://huggingface.co/spaces/black-forest-labs/FLUX.1-dev
- FLUX.2-dev by Black Forest Labs: https://huggingface.co/spaces/black-forest-labs/FLUX.2-dev
- Stable Diffusion 3.5 Large: https://huggingface.co/spaces/stabilityai/stable-diffusion-3.5-large
- You may need to agree to share your contact information to access this model. there is a form with contact info you have to fill out.
- SDXL Turbo Image to Image/Text to Image:https://huggingface.co/spaces/diffusers/unofficial-SDXL-Turbo-i2i-t2i
- This can generate images in fewer steps than other models. For SDXL-Turbo, keep prompts concise as it doesn’t use “negative prompts.”
