Update app.py

app.py

@@ -3,52 +3,46 @@ import torch
 import numpy as np
 import modin.pandas as pd
 from PIL import Image
-from diffusers import StableDiffusion3Pipeline #DiffusionPipeline #, StableDiffusion3Pipeline
+from diffusers import DiffusionPipeline #, StableDiffusion3Pipeline
 from huggingface_hub import hf_hub_download
-from diffusers import BitsAndBytesConfig, SD3Transformer2DModel
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 torch.cuda.max_memory_allocated(device=device)
-torch.cuda.empty_cache() 
+torch.cuda.empty_cache()
 
-model_id = "stabilityai/stable-diffusion-3.5-large-turbo"
-
-nf4_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
-model_nf4 = SD3Transformer2DModel.from_pretrained(
-    model_id,
-    subfolder="transformer",
-    quantization_config=nf4_config,
-    torch_dtype=torch.bfloat16
-)
-
-t5_nf4 = T5EncoderModel.from_pretrained("diffusers/t5-nf4", torch_dtype=torch.bfloat16)
-
-pipeline = StableDiffusion3Pipeline.from_pretrained(
-    model_id, 
-    transformer=model_nf4,
-    text_encoder_3=t5_nf4,
-    torch_dtype=torch.bfloat16
-)
-pipeline.enable_model_cpu_offload()
-
-def genie (Prompt, height, width, seed):
+def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed):
     generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
        
-    image = pipeline(Prompt, num_inference_steps=4, height=height, width=width, guidance_scale=0.0,).images[0]
+    if Model == "PhotoReal":
+        pipe = DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.9.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.9.1")
+        pipe.enable_xformers_memory_efficient_attention()
+        pipe = pipe.to(device)
+        torch.cuda.empty_cache()
+    
+        image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+        torch.cuda.empty_cache()
+        return image
+    
+    if Model == "Animagine XL 4":
+        animagine = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-4.0", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-4.0")
+        animagine.enable_xformers_memory_efficient_attention()
+        animagine = animagine.to(device)
+        torch.cuda.empty_cache()
+        
+        image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+        torch.cuda.empty_cache()
+        return image
 
+    
     return image
     
-gr.Interface(fn=genie, inputs=[#gr.Radio(['PhotoReal', 'Animagine XL 4',], value='PhotoReal', label='Choose Model'),
+gr.Interface(fn=genie, inputs=[gr.Radio(['PhotoReal', 'Animagine XL 4',], value='PhotoReal', label='Choose Model'),
                                gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), 
-                               #gr.Textbox(label='What you Do Not want the AI to generate. 77 Token Limit'),
+                               gr.Textbox(label='What you Do Not want the AI to generate. 77 Token Limit'),
                                gr.Slider(512, 1024, 768, step=128, label='Height'),
                                gr.Slider(512, 1024, 768, step=128, label='Width'),
-                               #gr.Slider(3, maximum=12, value=5, step=.25, label='Guidance Scale', info="5-7 for PhotoReal and 7-10 for Animagine"), 
-                               #gr.Slider(25, maximum=50, value=25, step=25, label='Number of Iterations'), 
+                               gr.Slider(3, maximum=12, value=5, step=.25, label='Guidance Scale', info="5-7 for PhotoReal and 7-10 for Animagine"), 
+                               gr.Slider(25, maximum=50, value=25, step=25, label='Number of Iterations'), 
                                gr.Slider(minimum=0, step=1, maximum=9999999999999999, randomize=True, label='Seed: 0 is Random'), 
                                ],
              outputs=gr.Image(label='Generated Image'),