{"id":114,"date":"2025-01-22T11:54:55","date_gmt":"2025-01-22T11:54:55","guid":{"rendered":"https:\/\/yu-ki.org\/?p=114"},"modified":"2025-07-11T14:31:12","modified_gmt":"2025-07-11T14:31:12","slug":"bildgenerierung-am-beispiel-von-veranstaltungen","status":"publish","type":"post","link":"https:\/\/yu-ki.org\/en\/2025\/01\/22\/bildgenerierung-am-beispiel-von-veranstaltungen\/","title":{"rendered":"Image generation"},"content":{"rendered":"

Introduction<\/strong><\/h2>\n\n\n\n

The creation of images was long a creative process that artists, <\/em>was previously reserved for designers and illustrators. In recent years, a completely new approach has emerged with the use of Artificial Intelligence (AI): images can now be generated automatically \u2013 often solely from a text-based description (prompt).<\/p>\n\n\n\n

This development opens up diverse possibilities, from quick sketches to complex illustrations and photorealistic visualizations. Nonprofit organizations, businesses, and individuals can create content significantly faster and more affordably as a result.<\/p>\n\n\n\n

\n\n\n\n

Basics<\/strong><\/h2>\n\n\n\n

AI-based image generation utilizes neural networks (especially so-called diffusion models<\/em> or Generative Adversarial Networks<\/em>Generative Adversarial Networks<\/p>\n\n\n\n

The AI was trained on millions of images and can create completely new motifs from them that didn't exist before. The result depends heavily on the quality and precision of the text description.<\/p>\n\n\n\n

\n\n\n\n

Areas of application & possible uses<\/strong><\/h2>\n\n\n\n
    \n
  • Social Media & Public Relations:<\/strong> Creation of post images, banners, or key visuals.<\/li>\n\n\n\n
  • Campaigns & Flyers:<\/strong> Development of unique illustrations for events or projects.<\/li>\n\n\n\n
  • Education & Training<\/strong> Visualizing abstract topics in presentations.<\/li>\n\n\n\n
  • Web Design<\/strong> Hero images or backgrounds.<\/li>\n\n\n\n
  • Storytelling & Books<\/strong> Cover or accompanying illustrations.<\/li>\n<\/ul>\n\n\n\n
    \n\n\n\n

    Step-by-step procedure<\/strong><\/h2>\n\n\n\n

    Step 1: Define Goal<\/h3>\n\n\n\n
      \n
    • Should the image be informative, decorative, emotional, or abstract?<\/li>\n\n\n\n
    • What medium is it intended for? (e.g., web, print, social media)<\/li>\n<\/ul>\n\n\n\n

      Step 2: Consider style and content<\/h3>\n\n\n\n
        \n
      • What style fits? (e.g., photorealistic, watercolor, comic)<\/li>\n\n\n\n
      • What exactly should be depicted?<\/li>\n<\/ul>\n\n\n\n

        Step 3: Formulate a request to the AI<\/h3>\n\n\n\n

        A good prompt<\/strong> For image generation, the following elements should be included:<\/p>\n\n\n\n

          \n
        • Motivation Description:<\/strong> What should be in the picture?<\/li>\n\n\n\n
        • Style and atmosphere:<\/strong> Should the image be bright, dark, realistic, or fantastical?<\/li>\n\n\n\n
        • Details:<\/strong> Colors, perspectives, background, emotions.<\/li>\n\n\n\n
        • Formatting instructions (optional):<\/strong> Aspect ratio, resolution.<\/li>\n<\/ul>\n\n\n\n

          Step 4: Check Results<\/h3>\n\n\n\n
            \n
          • Check image for fit.<\/li>\n\n\n\n
          • If necessary, refine with revised prompts.<\/li>\n<\/ul>\n\n\n\n

            Step 5: Download and save image<\/h3>\n\n\n\n
              \n
            • Observe license and terms of use. <\/li>\n\n\n\n
            • Choose a suitable format (e.g., PNG or JPEG).<\/li>\n<\/ul>\n\n\n\n
              \n\n\n\n

              Example from practice<\/h2>\n\n\n\n

              Scenario<\/h3>\n\n\n\n

              A non-profit organization wants to create an image for a flyer promoting a new meeting caf\u00e9 for refugees.<\/p>\n\n\n\n

              Prompt for an AI<\/h3>\n\n\n\n
              \n

              Create an inviting image of a caf\u00e9 with large windows, plants, and cozy wooden tables. Show people of different ages and backgrounds, enjoying coffee and conversing together. Style: friendly, colorful illustration, slightly sketchy, with a positive, warm mood.<\/p>\n<\/blockquote>\n\n\n\n

              \n\n\n\n

              Conclusion<\/h2>\n\n\n\n

              AI image generation allows for the creation of individual, emotional, and visually appealing motifs in a short amount of time. For non-profit organizations, this means greater creative freedom at lower costs\u2014and a new way to tell stories and convey messages. At the same time, it remains important to carefully align imagery and target audience.<\/p>\n\n\n\n

              \n\n\n\n

              Further links<\/h2>\n\n\n\n
              Midjourney Basic<\/a><\/td>Discord-based image generator. Delivers high-quality, artistic images from text prompts with style parameters and \"Relax Mode\" for unlimited generation without GPU limits.<\/td><\/tr>
              Krea AI Basic<\/a><\/td>Real-time generator with in-painting and ControlNet-like controls. Ideal for social media visuals; allows training of custom style presets.<\/td><\/tr>
              Flux AI Basic<\/a><\/td>Web interface for Stable Diffusion XL and Dream Machine Video. 5,000 credits for images, logos, or short clips; privacy-compliant EU servers.<\/td><\/tr>
              Leonardo Apprentice<\/a><\/td>Focus on game assets and concept art. Includes community models, tiling options, 4\u00d7 upscaling and continuous training slots.<\/td><\/tr>
              Adobe Firefly Standard<\/a><\/td>Generates images, text effects and future video with a commercial license. Seamless interaction with Photoshop, Express and Illustrator.<\/td><\/tr>
              Recraft V3<\/a><\/td>Specializing in vector and SVG output. Pay-per-image billing; ideal for logos, icons, and scalable graphics.<\/td><\/tr>
              Stable Diffusion OSS<\/a><\/td>Open source text-to-image model. Complete offline execution with community add-ons (LoRA, ControlNet); no license costs.<\/td><\/tr>
              DALL-E 3 API<\/a><\/td>Text-to-Image Model from OpenAI. Higher coherence in text elements, API usage for own apps. Copyright guaranteed for generated images.<\/td><\/tr>
              Canva AI<\/a><\/td>Design suite with Firefly backend. Offers drag-and-drop templates, brand assets and generative replacements 'Magic Edit' - ideal for non-designers.<\/td><\/tr>
              Flux Context Pro<\/a><\/td>Enhanced version of Flux with 15,000 credits, private prompt history, and workflow automation for agencies.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

              <\/p>","protected":false},"excerpt":{"rendered":"

              Einleitung Die Erstellung von Bildern war lange ein kreativer Prozess, der K\u00fcnstler:innen, Designer:innen und Illustrator:innen vorbehalten war. In den letzten Jahren hat sich mit dem Einsatz von K\u00fcnstlicher Intelligenz (KI) ein v\u00f6llig neuer Zugang entwickelt: Bilder k\u00f6nnen heute automatisch erzeugt werden \u2013 oft allein aus einer textbasierten Beschreibung (Prompt). Diese Entwicklung er\u00f6ffnet vielf\u00e4ltige M\u00f6glichkeiten, von schnellen Skizzen […]<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[24],"tags":[33],"class_list":["post-114","post","type-post","status-publish","format-standard","hentry","category-bildbasierte-ki-anwendungen","tag-links"],"_links":{"self":[{"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/posts\/114","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/comments?post=114"}],"version-history":[{"count":8,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/posts\/114\/revisions"}],"predecessor-version":[{"id":491,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/posts\/114\/revisions\/491"}],"wp:attachment":[{"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/media?parent=114"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/categories?post=114"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/yu-ki.org\/en\/wp-json\/wp\/v2\/tags?post=114"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}