Update app.py

app.py

@@ -3,8 +3,8 @@ from diffusers import StableDiffusion3Pipeline
 import gradio as gr
 import os
 import transformers
+import numpy as np
 from transformers import T5Tokenizer, T5ForConditionalGeneration
-from huggingface_hub import snapshot_download
 import spaces
 
 HF_TOKEN = os.getenv("HF_TOKEN")
@@ -16,18 +16,11 @@ else:
     device = "cpu"
     print("Using CPU")
 
-# download sd3 medium weights
-model_path = snapshot_download(
-    repo_id="stabilityai/stable-diffusion-3-medium", 
-    revision="refs/pr/26",
-    repo_type="model", 
-    ignore_patterns=["*.md", "*..gitattributes"],
-    local_dir="stable-diffusion-3-medium",
-    token=HF_TOKEN,
-    )
 
+MAX_SEED = np.iinfo(np.int32).max
 
-# Initialize the pipeline and download the model
+
+# Initialize the pipeline and download the sd3 medium model
 pipe = StableDiffusion3Pipeline.from_pretrained(model_path, torch_dtype=torch.float16)
 pipe.to(device)
 
@@ -81,15 +74,15 @@ enhance_prompt = gr.Checkbox(label="Prompt Enhancement", info="Enhance your prom
 
 negative_prompt = gr.Textbox(label="Negative Prompt", info="Describe what you don't want in the image", value="deformed, distorted, disfigured, poorly drawn, bad anatomy, incorrect anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", placeholder="Ugly, bad anatomy...")
 
-num_inference_steps = gr.Number(label="Number of Inference Steps", precision=0, value=25)
+num_inference_steps = gr.Number(label="Number of Inference Steps", info="The number of denoising steps of the image. More denoising steps usually lead to a higher quality image at the cost of slower inference", precision=0, value=25)
 
-height = gr.Slider(label="Height", info="Height of the Image", minimum=256, maximum="1536", step=32, value=1024)
+height = gr.Slider(label="Height", info="Height of the Image", minimum=256, maximum=1344, step=32, value=1024)
 
-width = gr.Slider(label="Width", info="Width of the Image", minimum=256, maximum="1536", step=32, value=1024)
+width = gr.Slider(label="Width", info="Width of the Image", minimum=256, maximum=1344, step=32, value=1024)
 
-guidance_scale = gr.Number(minimum=0.1, value=7.5, label="Guidance Scale", info="The number of denoising steps of the image. More denoising steps usually lead to a higher quality image at the cost of slower inference")
+guidance_scale = gr.Slider(label="Guidance Scale", info="Controls how much the image generation process follows the text prompt. Higher values make the image stick more closely to the input text.", minimum=0.0, maximum=10.0, value=7.5, step=0.1)
 
-seed = gr.Slider(value=42, minimum=0, maximum=2**32-1, step=1, label="Seed", info="A starting point to initiate the generation process, put 0 for a random one")
+seed = gr.Slider(value=42, minimum=0, maximum=MAX_SEED, step=1, label="Seed", info="A starting point to initiate the generation process, put 0 for a random one")
 
 num_images_per_prompt = gr.Slider(label="Number of Images to generate with the settings",minimum=1, maximum=4, step=1, value=1)