Update app.py

app.py

@@ -8,14 +8,11 @@ import torch
 ldm_pipeline = LatentDiffusionPipeline.from_pretrained("CompVis/ldm-text2im-large-256")
 images = []
 
-def predict(prompt, steps=100, seed=42, guidance_scale=5.0):
+def predict(prompt, steps=100, seed=42, guidance_scale=6.0):
     torch.cuda.empty_cache()
     generator = torch.manual_seed(seed)
-    image = ldm_pipeline([prompt], generator=generator, num_inference_steps=steps, guidance_scale=guidance_scale)
-    image_processed = image.cpu().permute(0, 2, 3, 1)
-    image_processed = (image_processed + 1.0) * 127.5
-    image_processed = image_processed.clamp(0, 255).numpy().astype(np.uint8)
-    return PIL.Image.fromarray(image_processed[0])
+    images = ldm_pipeline([prompt], generator=generator, num_inference_steps=steps, eta=0.3, guidance_scale=guidance_scale)
+    return images[0]
 
 random_seed = random.randint(0, 2147483647)
 gr.Interface(
@@ -24,7 +21,7 @@ gr.Interface(
         gr.inputs.Textbox(label='Prompt', default='a chalk pastel drawing of a llama wearing a wizard hat'),
         gr.inputs.Slider(1, 100, label='Inference Steps', default=50, step=1),
         gr.inputs.Slider(0, 2147483647, label='Seed', default=random_seed, step=1),
-        gr.inputs.Slider(1.0, 20.0, label='Guidance Scale - how much the prompt will influence the results', default=5.0, step=0.1),
+        gr.inputs.Slider(1.0, 20.0, label='Guidance Scale - how much the prompt will influence the results', default=6.0, step=0.1),
     ],
     outputs=gr.Image(shape=[256,256], type="pil", elem_id="output_image"),
     css="#output_image{width: 256px}",