Re-try

app.py

@@ -4,8 +4,11 @@ from PIL import Image
 import base64 
 
 import torch
-#from diffusers import StableDiffusionPipeline
+
+from diffusers import EulerDiscreteScheduler
 from diffusers import StableDiffusionXLPipeline
+from diffusers import StableDiffusion3Pipeline
+from diffusers import StableDiffusionPipeline
 
 #from transformers import pipeline
 import gradio as gr
@@ -13,21 +16,45 @@ import gradio as gr
 # Set Hugging Face API (needed for gated models)
 hf_api_key = os.environ.get('HF_API_KEY')
 
+# Use the Euler scheduler here instead
+scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
+
+# Load the Stable Diffusion pipeline
+model_id = "sd-legacy/stable-diffusion-v1-5"
+pipe = StableDiffusionPipeline.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use float16 on GPU, float32 on CPU
+    scheduler=scheduler,
+    use_auth_token=hf_api_key  # Required for gated model
+)
+
 # Load the Stable Diffusion pipeline
-#model_id = "runwayml/stable-diffusion-v1-5"
-#pipe = StableDiffusionPipeline.from_pretrained(
+#model_id = "stabilityai/stable-diffusion-3.5-medium"
+#pipe = SD3Transformer2DModel.from_pretrained(
 #    model_id,
+#    subfolder="transformer",
 #    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use float16 on GPU, float32 on CPU
 #    use_auth_token=hf_api_key  # Required for gated model
 #)
 
 # Load the Stable Diffusion XL pipeline
-model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-pipe = StableDiffusionXLPipeline.from_pretrained(
-    model_id,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use float16 on GPU, float32 on CPU
-    use_auth_token=hf_api_key  # Required for gated model
-)
+#model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+#pipe = StableDiffusionXLPipeline.from_pretrained(
+#    model_id,
+#    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use float16 on GPU, float32 on CPU
+#    use_auth_token=hf_api_key  # Required for gated model
+#)
+
+# Load the Stable Diffusion pipeline
+#model_id = "stabilityai/stable-diffusion-3-medium"
+#model_id = "stabilityai/stable-diffusion-3-medium-diffusers"
+#pipe = StableDiffusion3Pipeline.from_pretrained(
+#    model_id,
+#    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # Use float16 on GPU, float32 on CPU,
+#    scheduler=scheduler,
+#    use_auth_token=hf_api_key  # Required for gated model
+#)
+
 
 # Move pipeline to GPU if available
 device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -44,26 +71,10 @@ def base64_to_pil(img_base64):
     pil_image = Image.open(byte_stream)
     return pil_image
 
-def generate(prompt):
-    output = get_completion(prompt)
-    result_image = base64_to_pil(output)
-    return result_image
-
-#def generate(prompt, negative_prompt, steps, guidance, width, height):
-#    # Ensure width and height are multiples of 8 (required by Stable Diffusion)
-#    width = int(width) - (int(width) % 8)
-#    height = int(height) - (int(height) % 8)
-    
-#    # Generate image with Stable Diffusion
-#    output = pipe(
-#        prompt,
-#        negative_prompt=negative_prompt or None,  # Handle empty negative prompt
-#        num_inference_steps=int(steps),
-#        guidance_scale=float(guidance),
-#        width=width,
-#        height=height
-#    )
-#    return output.images[0]  # Return the first generated image (PIL format)
+#def generate(prompt):
+#    output = get_completion(prompt)
+#    result_image = base64_to_pil(output)
+#    return result_image
 
 # Generate function
 def generate(prompt, negative_prompt, steps, guidance, width, height):
@@ -82,6 +93,7 @@ def generate(prompt, negative_prompt, steps, guidance, width, height):
     )
     return output.images[0]  # Return the first generated image (PIL format)
 
+
 # Create Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# Image Generation with Stable Diffusion")