Update multimodalart/latentdiffusion

app.py

@@ -1,5 +1,8 @@
 """See https://huggingface.co/spaces/Gradio-Blocks/Story-to-video/blob/main/app.py."""
 import gradio as gr
+import base64
+import io
+from PIL import Image  # opencv-python
 
 # from PIL import Image
 # from transformers import AutoTokenizer, AutoModelForSeq2SeqLM,pipeline
@@ -8,6 +11,45 @@ import gradio as gr
 
 image_gen = gr.Interface.load("spaces/multimodalart/latentdiffusion")
 
-# image_bytes = image_gen(senten, steps, width, height, num_images, diversity)
 
-image_gen.launch()
+def generate_images(phrase: str):
+    generated_text = phrase
+    steps = 125
+    width = 256
+    height = 256
+    num_images = 4
+    num_images = 1
+    diversity = 6
+
+    image_bytes = image_gen(generated_text, steps, width, height, num_images, diversity)
+
+    # Algo from spaces/Gradio-Blocks/latent_gpt2_story/blob/main/app.py
+    # generated_images = []
+
+    img = None
+    for image in image_bytes[1]:
+        image_str = image[0]
+        try:
+            image_str = image_str.replace("data:image/png;base64,", "")
+        except Exception as exc:
+            logger.error(exc)
+            return None
+        decoded_bytes = base64.decodebytes(bytes(image_str, "utf-8"))
+        img = Image.open(io.BytesIO(decoded_bytes))
+
+        # generated_images.append(img)
+
+    # return generated_images
+    return img
+
+
+examples = ["an apple", "Donald Trump"]
+
+iface = gr.Interface(
+    generate_images,
+    "text",
+    "image",
+    examples=examples,
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+logzero
+opencv-python