return just one image

app.py

@@ -10,7 +10,7 @@ def generate_image_predictions(prompt):
 iface = gr.Interface(
     fn=generate_image_predictions,
     inputs=gr.components.Textbox(label="Enter a text prompt here"),
-    outputs=[gr.components.Image(label="Output Image") for i in range(4)],
+    outputs=gr.components.Image(label="Output Image"),
     title="Map Diffuser",
     description="Generates four images from a given text prompt.",
     examples=[["Satellite image of amsterdam with industrial area and highways"], [

inference_code.py

@@ -4,11 +4,11 @@ from flax.jax_utils import replicate
 from flax.training.common_utils import shard
 from diffusers import FlaxStableDiffusionPipeline
 
+model_path = "sabman/map-diffuser-v3"
+pipeline, _params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
 
 # prompt = "create a map with traffic signals, busway and residential buildings, in water color style"
 def generate_images(prompt):
-    model_path = "sabman/map-diffuser-v3"
-    pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
 
     prng_seed = jax.random.PRNGKey(-1)
     num_inference_steps = 50
@@ -18,11 +18,11 @@ def generate_images(prompt):
     prompt_ids = pipeline.prepare_inputs(prompt)
 
     # shard inputs and rng
-    params = replicate(params)
+    params = replicate(_params)
     prng_seed = jax.random.split(prng_seed, jax.device_count())
     prompt_ids = shard(prompt_ids)
 
     images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
     images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
 
-    return [images[0], images[1], images[2], images[3]]
+    return images[0]