update docs

Signed-off-by: Alexandros Pappas <apappascs@gmail.com>

Author: apappascs

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/image/openai-image.adoc

@@ -170,14 +170,16 @@ For example to override the OpenAI specific options such as quality and the numb
 ImageResponse response = openaiImageModel.call(
         new ImagePrompt("A light cream colored mini golden doodle",
         OpenAiImageOptions.builder()
-                .quality("hd")
+                .model("dall-e-2")  // dall-e-2 supports generating multiple images
                 .N(4)
                 .height(1024)
                 .width(1024).build())
 
 );
 ----
 
+NOTE: Only DALL-E 2 supports generating multiple images (n > 1). For DALL-E 3 and GPT-Image models, n must be 1.
+
 TIP: In addition to the model specific https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiImageOptions.java[OpenAiImageOptions] you can use a portable https://github.com/spring-projects/spring-ai/blob/main/spring-ai-model/src/main/java/org/springframework/ai/image/ImageOptions.java[ImageOptions] instance, created with the https://github.com/spring-projects/spring-ai/blob/main/spring-ai-model/src/main/java/org/springframework/ai/image/ImageOptionsBuilder.java[ImageOptionsBuilder#builder()].
 
 == Streaming Image Generation
@@ -249,7 +251,7 @@ OpenAiImageOptions options = OpenAiImageOptions.builder()
     .size("1536x1024")
     .quality("high")
     .background("transparent")
-    .outputFormat("png")
+    .outputFormat("jpeg")
     .outputCompression(85)
     .build();
 

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/imageclient.adoc

@@ -34,6 +34,7 @@ For models that support streaming image generation, Spring AI provides the link:
 
 [source,java]
 ----
+@FunctionalInterface
 public interface StreamingImageModel extends StreamingModel<ImagePrompt, ImageResponse> {
 
 	Flux<ImageResponse> stream(ImagePrompt prompt);
@@ -43,7 +44,21 @@ public interface StreamingImageModel extends StreamingModel<ImagePrompt, ImageRe
 
 The `StreamingImageModel` interface allows AI models to generate images progressively, emitting partial images as they are being created. This provides a better user experience by showing incremental progress rather than waiting for the final image.
 
-NOTE: Streaming image generation is currently only supported by certain models like OpenAI's GPT-Image models (gpt-image-1 and gpt-image-1-mini). Traditional models like DALL-E do not support streaming.
+**Example Usage:**
+
+[source,java]
+----
+ImageOptions options = OpenAiImageOptions.builder()
+    .model("gpt-image-1-mini")
+    .stream(true)
+    .partialImages(2)
+    .build();
+
+ImagePrompt prompt = new ImagePrompt("A mountain landscape", options);
+Flux<ImageResponse> stream = streamingImageModel.stream(prompt);
+----
+
+IMPORTANT: Streaming image generation is currently only supported by OpenAI's GPT-Image models (`gpt-image-1` and `gpt-image-1-mini`).
 
 === ImagePrompt
 

spring-ai-model/src/main/java/org/springframework/ai/image/StreamingImageModel.java

@@ -21,49 +21,47 @@
 import org.springframework.ai.model.StreamingModel;
 
 /**
- * The StreamingImageModel interface provides a reactive API for invoking image generation
- * models with streaming response. This enables progressive image generation where partial
- * images are emitted as they become available during the generation process.
+ * Reactive API for streaming image generation. Emits progressive image updates during
+ * generation, enabling real-time user feedback.
  *
  * <p>
- * Streaming image generation is particularly useful for providing real-time feedback to
- * users during long-running image generation tasks. Depending on the model and
- * configuration, the stream may emit:
+ * The stream emits partial images (if configured) followed by the final complete image.
+ * Partial images are best-effort and model-dependent.
  * </p>
- * <ul>
- * <li>Partial images at various stages of completion</li>
- * <li>The final complete image</li>
- * </ul>
  *
  * <p>
  * Example usage:
  * </p>
  *
  * <pre>{@code
- * ImagePrompt prompt = new ImagePrompt("A serene mountain landscape");
- * Flux<ImageResponse> imageStream = streamingImageModel.stream(prompt);
- * imageStream.subscribe(response -> {
- * 	// Process each partial or final image response
- * 	Image image = response.getResult().getOutput();
- * 	// Display or save the image
+ * ImageOptions options = OpenAiImageOptions.builder()
+ *     .model("gpt-image-1-mini")
+ *     .stream(true)
+ *     .partialImages(2)
+ *     .build();
+ *
+ * ImagePrompt prompt = new ImagePrompt("A serene mountain landscape", options);
+ * Flux<ImageResponse> stream = streamingImageModel.stream(prompt);
+ *
+ * stream.subscribe(response -> {
+ *     Image image = response.getResult().getOutput();
+ *     displayImage(image.getB64Json());
  * });
  * }</pre>
  *
  * @author Alexandros Pappas
  * @since 1.1.0
  * @see ImageModel
- * @see StreamingModel
  * @see ImagePrompt
  * @see ImageResponse
  */
 @FunctionalInterface
 public interface StreamingImageModel extends StreamingModel<ImagePrompt, ImageResponse> {
 
 	/**
-	 * Executes streaming image generation for the given prompt.
-	 * @param request the image generation request containing the prompt and options
-	 * @return a reactive stream of image responses, potentially including partial images
-	 * during generation and the final complete image
+	 * Streams image generation responses for the given prompt.
+	 * @param request the image prompt with generation options
+	 * @return reactive stream emitting partial images (if configured) and the final image
 	 */
 	@Override
 	Flux<ImageResponse> stream(ImagePrompt request);