[diffusion] apps: support I2I tasks in webui (#15778)

python/sglang/multimodal_gen/apps/webui/main.py

@@ -22,6 +22,7 @@ def add_webui_args(parser: argparse.ArgumentParser):
 
 def run_sgl_diffusion_webui(server_args: ServerArgs):
     # import gradio in function to avoid CI crash
+
     import gradio as gr
 
     # init client
@@ -31,6 +32,7 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
     def gradio_generate(
         prompt,
         negative_prompt,
+        reference_image_paths_str,
         seed,
         num_frames,
         frames_per_second,
@@ -45,9 +47,23 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
         So we use global variable sampling_params_kwargs to avoid pass this param, because gradio does not support this.
         return [ np.ndarray, None ] | [None, np.ndarray]
         """
+        if (
+            reference_image_paths_str is not ""
+            and reference_image_paths_str is not None
+        ):
+            if "，" in reference_image_paths_str:
+                print(
+                    f"Warning: please use English comma to separate the reference image paths, and the reference image paths is: {reference_image_paths_str}"
+                )
+                reference_image_paths_str = reference_image_paths_str.replace("，", ",")
+            image_path = [path.strip() for path in reference_image_paths_str.split(",")]
+        else:
+            image_path = None
+
         sampling_params_kwargs = dict(
             prompt=prompt,
             negative_prompt=negative_prompt,
+            image_path=image_path,
             seed=seed,
             num_frames=num_frames,
             fps=frames_per_second,
@@ -68,6 +84,11 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
         )
         result = sync_scheduler_client.forward([batch])
         save_file_path = str(os.path.join(batch.output_path, batch.output_file_name))
+        if result.output is None:
+            raise ValueError(
+                f"No output is generated by client, and their sampling params is: \n{ '\n'.join([f'{key}: {value}' for key, value in sampling_params_kwargs.items()])}"
+            )
+
         frames = post_process_sample(
             result.output[0],
             batch.data_type,
@@ -104,6 +125,10 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
                 frames_per_second = gr.Slider(
                     minimum=4, maximum=60, value=16, step=1, label="frames_per_second"
                 )
+                reference_image_paths_str = gr.Textbox(
+                    label="reference images",
+                    placeholder="Examples: 'image1.png, image2.png' or 'https://example.com/image1.png, https://example.com/image2.png'",
+                )
                 width = gr.Number(label="width", precision=0, value=720)
                 height = gr.Number(label="height", precision=0, value=480)
                 num_inference_steps = gr.Slider(
@@ -127,6 +152,7 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
             inputs=[
                 prompt,
                 negative_prompt,
+                reference_image_paths_str,
                 seed,
                 num_frames,
                 frames_per_second,
@@ -143,6 +169,7 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
             server_port=server_args.webui_port,
             quiet=True,
             prevent_thread_lock=True,
+            show_error=True,
         )
 
         # print banner