{"id":1919,"date":"2026-03-08T22:42:07","date_gmt":"2026-03-09T02:42:07","guid":{"rendered":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/?p=1919"},"modified":"2026-03-10T19:16:22","modified_gmt":"2026-03-10T23:16:22","slug":"image-prompting-guide","status":"publish","type":"post","link":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/images-module\/image-prompting-guide\/","title":{"rendered":"Image Prompting Guide"},"content":{"rendered":"\n

This guide will help you craft strong text prompts for creating and editing images with Adobe Firefly and Photoshop\u2019s Generative Fill.<\/p>\n\n\n\n

Both use the same underlying idea \u2014 a diffusion model trained to create or modify images based on text descriptions \u2014 but the way you interact with them differs.<\/p>\n\n\n\n

Note that the instructions and concepts used to prompt Firefly can also be used in other chat-to-image interfaces like those provided by Copilot<\/a>, Gemini<\/a> and chatGPT<\/a>. All of those tools required sign-in. You can sign in with your CUNY credentials to Copilot.<\/p>\n\n\n\n

\ud83d\udd39 Part 1: One Shot Prompts<\/h2>\n\n\n\n

Firefly is Adobe\u2019s web-based generative image tool.<\/p>\n\n\n\n

In this method, you enter a text prompt, and the system generates full images based on your description.<\/p>\n\n\n\n

Prompting in Adobe Firefly<\/strong><\/h3>\n\n\n\n

We are going to use Firefly: https:\/\/firefly.adobe.com<\/a><\/p>\n\n\n\n

Make sure you’re signed in (CUNYFirst credentials) so you can save outputs and more.<\/p>\n\n\n\n

Firefly is Adobe\u2019s web-based generative image tool. Other image generation tools are similar especially in the prompting structure shown below. You can use these lessons in other tools.<\/p>\n\n\n\n

How Firefly Understands Prompts<\/strong><\/h3>\n\n\n\n

Firefly reads your words as a set of visual instructions \u2014 nouns describe subjects, adjectives set style and tone, and context defines relationships.<\/p>\n\n\n\n

For example:<\/p>\n\n\n\n

\u201cA realistic portrait of a woman wearing headphones, sitting in a recording studio lit by blue and orange neon light.\u201d<\/p>\n\n\n\n

If you do not provide enough information, it will not ask you for more information but rather construct the image based on relationships and associations it has stored in its model. So, the less guidance you give the model, the more your image will look like the average of whatever nouns you put in the prompt. The “average” depends on the training data of the model and includes whatever biases or lack of information was present.<\/p>\n\n\n\n

To help avoid that and make your images truer to the idea in your head and more unique, follow the prompting structure outlined next.<\/p>\n\n\n\n

Prompting Structure<\/strong><\/h3>\n\n\n\n

Firefly works best when your prompts include:<\/p>\n\n\n\n

    \n
  1. Subject<\/strong> \u2013 What\u2019s the main focus? (e.g., a mountain cabin, a city street at night)<\/li>\n\n\n\n
  2. Details<\/strong> \u2013 What defines it? (e.g., surrounded by trees, neon reflections, misty atmosphere)<\/li>\n\n\n\n
  3. Style<\/strong> or Medium<\/strong> \u2013 How should it look? (e.g., digital painting, cinematic photo, watercolor)<\/li>\n\n\n\n
  4. Lighting<\/strong> and Mood<\/strong> \u2013 Optional but adds realism (e.g., golden hour, dramatic shadows, foggy morning)<\/li>\n\n\n\n
  5. Camera<\/strong> or Composition<\/strong> \u2013 Optional (e.g., wide shot, macro, aerial view)<\/li>\n<\/ol>\n\n\n\n

    Here are two images, one with a less detailed prompt and one with more detail:<\/p>\n\n\n\n

    \n
    \n
    \"A
    AI generated image by Nano Banana 2 on 2026.03.08. Prompt: A woman walking a golden retriever dog in a park.<\/figcaption><\/figure>\n<\/div>\n\n\n\n
    \n
    \"A
    AI generated image by Nano Banana 2 on 2026.03.08. A woman walking a dog. Both dressed in steampunk attire. They are walking down a London street with other walkers, vehicles and shops in fictitious advanced steampunk era. It is late in day, just before golden hour. Cinematic style, medium shot with medium depth of field focused on the woman and dog.<\/figcaption><\/figure>\n<\/div>\n<\/div>\n\n\n\n

    Note that the same prompt can give different results in different models and sometimes they use past history (as done above with similar women, doc and positioning). Here is the same prompt (#2) in ChatGPT:<\/p>\n\n\n\n

    \"Woman<\/figure>\n\n\n\n

    Example Prompts<\/h3>\n\n\n\n
      \n
    • \u201cAn old lighthouse on a rocky coast, crashing waves and sea spray, dramatic clouds overhead, oil painting, stormy lighting, wide landscape composition.\u201d<\/li>\n\n\n\n
    • \u201cA digital illustration of a futuristic city skyline at sunset with flying cars and glowing signs.\u201d<\/li>\n<\/ul>\n\n\n\n

      Firefly Prompting Tips<\/h3>\n\n\n\n
        \n
      • Be specific but concise \u2014 aim for clarity, not long sentences.<\/li>\n\n\n\n
      • Start simple, then add details gradually.<\/li>\n\n\n\n
      • Use descriptive adjectives (realistic, cinematic, moody, painterly, symmetrical).<\/li>\n\n\n\n
      • Try style keywords like studio lighting, watercolor, macro lens, low angle.<\/li>\n\n\n\n
      • Use negative prompts (if available) to exclude things: \u201cwithout text overlay,\u201d \u201cno people.\u201d<\/li>\n<\/ul>\n\n\n\n

        Tip: Think of the prompt as your creative direction to an assistant \u2014 clear, visual, and intentional.<\/p>\n\n\n\n

        Here are 2 examples showing style changes:<\/p>\n\n\n\n

        \"A
        AI generated by ChatGPT 2026.03.08. Prompt: A small house beside a lake, pine trees reflected in the water, realistic photograph, sunrise lighting, wide shot.<\/figcaption><\/figure>\n\n\n\n
        \"A
        AI generated by ChatGPT 2026.03.08. Prompt: A small house beside a lake, pine trees reflected in the water, pixel art, early morning mood, side view.<\/figcaption><\/figure>\n\n\n\n

        \ud83d\udd39 Part 2: Prompting for Photoshop\u2019s Generative Fill<\/h2>\n\n\n\n

        Photoshop\u2019s Generative Fill lets you use prompts to add, replace, or remove content within an image or blank document.<\/p>\n\n\n\n

        It\u2019s not about generating the entire scene at once \u2014 instead, you build it piece by piece.<\/p>\n\n\n\n

        The Workflow<\/h3>\n\n\n\n
          \n
        1. Start with a Blank Canvas\n
            \n
          • Create a new Photoshop document (e.g., 1000\u00d71000 px).<\/li>\n\n\n\n
          • Choose a transparent background color.<\/li>\n<\/ul>\n<\/li>\n\n\n\n
          • Select the Canvas\n
              \n
            • Use the Rectangular Marquee Tool to select the whole area.<\/li>\n\n\n\n
            • Go to the Contextual Task Bar \u2192 Generative Fill.<\/li>\n<\/ul>\n<\/li>\n\n\n\n
            • Generate the Background\n
                \n
              • Enter a detailed prompt for your background.<\/li>\n\n\n\n
              • Example:<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n

                \u201cA misty forest at dawn with golden light filtering through tall pine trees.\u201d<\/p>\n\n\n\n

                  \n
                • Click Generate and review the results. Choose one that works best.<\/li>\n<\/ul>\n\n\n\n
                  \"AI
                  Single Prompt. Generated by AI in Photoshop with Firefly Fill and Expand model on 2026.03.08<\/figcaption><\/figure>\n\n\n\n
                    \n
                  1. Add New Elements\n
                      \n
                    • Use the Marquee or Lasso tool to create a smaller selection in the area where you want to add an object.<\/li>\n\n\n\n
                    • Go to Generative Fill again and write a prompt for that item.<\/li>\n\n\n\n
                    • Example:<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n

                      \u201cA wooden cabin sitting in a clearing with smoke rising from the chimney.\u201d<\/p>\n\n\n\n

                      \"AI
                      2 prompts (forest background, cabin). Generated by AI in Photoshop with Firefly Fill and Expand model on 2026.03.08<\/figcaption><\/figure>\n\n\n\n
                        \n
                      • Photoshop fills the selected area, blending it with your existing background.<\/li>\n<\/ul>\n\n\n\n
                          \n
                        1. Refine and Build\n
                            \n
                          • Repeat the process for additional elements \u2014 a person, a building, an animal, or a vehicle.<\/li>\n\n\n\n
                          • Adjust selections for scale and composition.<\/li>\n\n\n\n
                          • Try variations if something doesn\u2019t blend well.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n

                            “an alien space ship hovering and inspecting the ground”<\/p>\n\n\n\n

                            \"AI
                            3 prompts (forest background, cabin, flying saucer). Generated by AI in Photoshop with Firefly Fill and Expand model on 2026.03.08<\/figcaption><\/figure>\n\n\n\n

                            <\/p>\n\n\n\n

                            Prompting Tips for Generative Fill<\/strong><\/h3>\n\n\n\n
                              \n
                            • Describe context, not just objects:<\/li>\n\n\n\n
                            • \u201cA red umbrella on a rainy street with reflections\u201d works better than \u201cumbrella.\u201d<\/li>\n\n\n\n
                            • Think spatially: mention background, foreground, lighting, and distance.<\/li>\n\n\n\n
                            • Use multiple smaller prompts instead of one large prompt.<\/li>\n\n\n\n
                            • Photoshop\u2019s AI blends local selections more effectively than trying to generate everything at once.<\/li>\n\n\n\n
                            • Experiment: run the same prompt multiple times \u2014 results will differ each time.<\/li>\n\n\n\n
                            • Avoid clutter: too many objects or unrelated styles in one prompt can confuse the model.<\/li>\n<\/ul>\n\n\n\n

                              Comparing Firefly and Photoshop<\/h2>\n\n\n\n
                              Feature<\/strong><\/td>Adobe Firefly<\/strong><\/td>Photoshop Generative Fill<\/strong><\/td><\/tr>
                              Purpose<\/td>Create entire images from text<\/td>Edit or build images piece by piece<\/td><\/tr>
                              Best For<\/td>Starting from scratch<\/td>Adding, replacing, or refining<\/td><\/tr>
                              Prompt Style<\/td>One complete description<\/td>Multiple focused prompts<\/td><\/tr>
                              Output Control<\/td>Global (whole image)<\/td>Local (selected regions)<\/td><\/tr>
                              Use Case Example<\/td>Generate a cinematic desert landscape.<\/td>Add a hiker on the left side of the desert scene.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

                              \ud83d\udd0d Key Takeaways<\/h3>\n\n\n\n
                                \n
                              • Both Firefly and Photoshop use diffusion models that generate images by gradually removing noise guided by your prompt.<\/li>\n\n\n\n
                              • Firefly is ideal for creating \u2014 start with words and make a full image.<\/li>\n\n\n\n
                              • Photoshop is ideal for compositing \u2014 use text prompts and selections to build up an image in layers.<\/li>\n\n\n\n
                              • Always review the output critically: consider realism, coherence, and ethical use (licensing, representation, and transparency).<\/li>\n<\/ul>\n\n\n\n

                                \u2705 Practice Challenge combining the two<\/h2>\n\n\n\n

                                This is optional<\/p>\n\n\n\n

                                  \n
                                1. Use a chat-based tool (Firefly, Copilot, Gemini) to generate a full background image.\n
                                    \n
                                  1. remember to save your prompt in the Project Description Document<\/li>\n<\/ol>\n<\/li>\n\n\n\n
                                  2. Import it into Photoshop and use Selection and Generative Fill to add 2\u20133 new elements that match your composition.<\/li>\n\n\n\n
                                  3. Save your .psd in the  project folder. Save the exported jpg in the Output files folder.<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

                                    This guide will help you craft strong text prompts for creating and editing images with Adobe Firefly and Photoshop\u2019s Generative Fill. Both use the same underlying idea \u2014 a diffusion model trained to create or modify images based on text descriptions \u2014 but the way you interact with them differs. Note that the instructions and […]<\/p>\n","protected":false},"author":16,"featured_media":1926,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"portfolio_post_id":0,"portfolio_citation":"","portfolio_annotation":"","openlab_post_visibility":"","footnotes":""},"categories":[34],"tags":[57,56,58,59,54,55],"class_list":["post-1919","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-images-module","tag-ai","tag-genai","tag-guide","tag-how-to","tag-prompt","tag-prompting"],"_links":{"self":[{"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/posts\/1919","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/comments?post=1919"}],"version-history":[{"count":9,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/posts\/1919\/revisions"}],"predecessor-version":[{"id":1984,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/posts\/1919\/revisions\/1984"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/media\/1926"}],"wp:attachment":[{"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/media?parent=1919"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/categories?post=1919"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/openlab.bmcc.cuny.edu\/mmp100-stein\/wp-json\/wp\/v2\/tags?post=1919"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}