[bugfix] Return individual images for batched image API requests (#1917)

For n > 1, the image endpoints returned one preview grid instead of n images.
The endpoints now run one model batch, save each decoded sample as its own file,
and return one URL or base64 item for each image. This applies to generations
and edits.

A keyword-only return_samples field (default False) is added to OutputConfig,
SamplingParam and ForwardBatch. Batched image requests set it and do not build
preview frames. The worker keeps the sample tensor for these requests, and
non-output ranks clear the field. Defaults and positional arguments do not
change.

docs/getting_started/v1_api.md

@@ -40,3 +40,11 @@ The following two classes `PipelineConfig` and `SamplingParam` are used to confi
       members:
         - from_pretrained
       heading_level: 4
+
+### Returning samples without previews
+
+Set `OutputConfig(return_samples=True, return_frames=False, save_video=False)`
+to receive the decoded CPU tensor in `GenerationResult.samples` without building
+preview grids or writing media. Pixel samples retain the existing float `[0, 1]`
+contract. `return_frames=True` continues to return both samples and preview frames.
+The legacy sampling/keyword interface accepts the same `return_samples` option.