Update app.py

app.py

@@ -6,17 +6,32 @@ import gradio as gr
 import numpy as np
 import torch
 from PIL import Image
-from diffusers import StableDiffusionXLPipeline, EDMEulerScheduler, StableDiffusionXLInstructPix2PixPipeline, AutoencoderKL
+from diffusers import StableDiffusionXLPipeline, EDMEulerScheduler, StableDiffusionXLInstructPix2PixPipeline, AutoencoderKL, EulerAncestralDiscreteScheduler
 from custom_pipeline import CosStableDiffusionXLInstructPix2PixPipeline
 from huggingface_hub import hf_hub_download
 from huggingface_hub import InferenceClient
-from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel, FlowMatchEulerDiscreteScheduler
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.float16
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+
+repo = "fluently/Fluently-XL-Final"
+
+pipe_best = StableDiffusionXLPipeline.from_pretrained(repo, torch_dtype=torch.float16, vae=vae)
+pipe_best.load_lora_weights("ehristoforu/dalle-3-xl-v2", weight_name="dalle-3-xl-lora-v2.safetensors", adapter_name="dalle")
+pipe_best.load_lora_weights("KingNish/Better-Image-XL-Lora", weight_name="example-03.safetensors", adapter_name="lora")
+pipe_best.set_adapters(["lora","dalle"], adapter_weights=[1.5, 0.5])
+pipe_best.to("cuda")
 
-repo = "stabilityai/stable-diffusion-3-medium-diffusers"
-pipe = StableDiffusion3Pipeline.from_pretrained(repo, torch_dtype=torch.float16).to(device)
+pipe_3D = StableDiffusionXLPipeline.from_pretrained(repo, torch_dtype=torch.float16, vae=vae)
+pipe_3D.load_lora_weights("artificialguybr/3DRedmond-V1", weight_name="3DRedmond-3DRenderStyle-3DRenderAF.safetensors", adapter_name="3D")
+pipe_3D.set_adapters(["3D"])
+pipe_3D.to("cuda")
+
+pipe_logo = StableDiffusionXLPipeline.from_pretrained(repo, torch_dtype=torch.float16, vae=vae)
+pipe_logo.load_lora_weights("artificialguybr/LogoRedmond-LogoLoraForSDXL", weight_name="LogoRedmond_LogoRedAF.safetensors", adapter_name="logo")
+pipe_logo.set_adapters(["logo"])
+pipe_logo.to("cuda")
 
 help_text = """
 To optimize image results:
@@ -44,7 +59,6 @@ def set_timesteps_patched(self, num_inference_steps: int, device = None):
 # Image Editor
 edit_file = hf_hub_download(repo_id="stabilityai/cosxl", filename="cosxl_edit.safetensors")
 EDMEulerScheduler.set_timesteps = set_timesteps_patched
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
 pipe_edit = StableDiffusionXLInstructPix2PixPipeline.from_single_file(
     edit_file, num_in_channels=8, is_cosxl_edit=True, vae=vae, torch_dtype=torch.float16,
 )
@@ -52,7 +66,7 @@ pipe_edit.scheduler = EDMEulerScheduler(sigma_min=0.002, sigma_max=120.0, sigma_
 pipe_edit.to("cuda")
 
 # Generator
-@spaces.GPU(duration=30, queue=False)
+@spaces.GPU(duration=45, queue=False)
 def king(type ,
         input_image ,
         instruction: str ,
@@ -63,7 +77,7 @@ def king(type ,
         image_cfg_scale: float = 1.7,
         width: int = 1024,
         height: int = 1024,
-        guidance_scale: float = 6,
+        style="BEST",
         use_resolution_binning: bool = True,
         progress=gr.Progress(track_tqdm=True),
     ):
@@ -85,14 +99,14 @@ def king(type ,
         if randomize_seed:
             seed = random.randint(0, 99999)
         generator = torch.Generator().manual_seed(seed)
-        image = pipe(
-            prompt = instruction,
-            guidance_scale = 7, 
-            num_inference_steps = steps, 
-            width = width, 
-            height = height,
-            generator = generator
-        ).images[0]         
+        if style=="3D":
+            instruction = f"3DRenderAF, 3D Render, {instruction}"
+            image = pipe_3D( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
+        elif style=="Logo":
+            instruction = f"LogoRedAF, {instruction}"
+            image = pipe_logo( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
+        else:
+            image = pipe_best( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
         return seed, image
 
 client = InferenceClient()
@@ -162,10 +176,15 @@ with gr.Blocks(css=css) as demo:
             type = gr.Dropdown(["Image Generation","Image Editing"], label="Task", value="Image Generation",interactive=True, info="AI will select option based on your query, but if it selects wrong, please choose correct one.")
         with gr.Column(scale=1):
             generate_button = gr.Button("Generate")
-
+    with gr.Row():
+        style = gr.Radio(choices=["BEST","3D","Logo"],label="Style", value="BEST", interactive=True)
     with gr.Row():
         input_image = gr.Image(label="Image", type="pil", interactive=True)
 
+    with gr.Row():
+        width = gr.Number(value=1024, step=16,label="Width", interactive=True)
+        height = gr.Number(value=1024, step=16,label="Height", interactive=True)
+    
     with gr.Row():
         text_cfg_scale = gr.Number(value=7.3, step=0.1, label="Text CFG", interactive=True)
         image_cfg_scale = gr.Number(value=1.7, step=0.1,label="Image CFG", interactive=True)
@@ -188,9 +207,7 @@ with gr.Blocks(css=css) as demo:
     )
 
     gr.Markdown(help_text)
-
     instruction.change(fn=response, inputs=[instruction,input_image], outputs=type, queue=False)
-
     input_image.upload(fn=response, inputs=[instruction,input_image], outputs=type, queue=False)
     
     gr.on(triggers=[
@@ -206,6 +223,9 @@ with gr.Blocks(css=css) as demo:
                 seed,
                 text_cfg_scale,
                 image_cfg_scale,
+                width,
+                height,
+                style
             ],
             outputs=[seed, input_image],
         )