update for Sintetico Models

app.py

@@ -19,7 +19,7 @@ import stone
 import os
 import spaces
 
-access_token = os.getenv("AccessTokenSD3")
+# access_token = os.getenv("AccessTokenSD3")
 
 
 from huggingface_hub import login
@@ -28,71 +28,34 @@ login(token = access_token)
 
 # Define model initialization functions
 def load_model(model_name):
-    if model_name == "stabilityai/sdxl-turbo":
-        pipeline = DiffusionPipeline.from_pretrained(
-            model_name, 
-            torch_dtype=torch.float16, 
-            variant="fp16"
+    if model_name == "sinteticoXL":
+        pipeline = StableDiffusionXLPipeline.from_single_file(
+            "https://huggingface.co/lucianosb/sinteticoXL-models/blob/main/sinteticoXL_v1dot2.safetensors",
+            torch_dtype=torch.float16,
+            variant="fp16",
+            use_safetensors=True,
         ).to("cuda")
-    elif model_name == "runwayml/stable-diffusion-v1-5":
-        pipeline = StableDiffusionPipeline.from_pretrained(
-            model_name, 
-            torch_dtype=torch.float16
-        ).to("cuda")
-    elif model_name == "ByteDance/SDXL-Lightning":
-        base = "stabilityai/stable-diffusion-xl-base-1.0"
-        ckpt = "sdxl_lightning_4step_unet.safetensors"
-        unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
-        unet.load_state_dict(load_file(hf_hub_download(model_name, ckpt), device="cuda"))
-        pipeline = StableDiffusionXLPipeline.from_pretrained(
-            base, 
-            unet=unet, 
-            torch_dtype=torch.float16, 
-            variant="fp16"
-        ).to("cuda")
-        pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config, timestep_spacing="trailing")
-    elif model_name == "segmind/SSD-1B":
-        pipeline = StableDiffusionXLPipeline.from_pretrained(
-            model_name, 
-            torch_dtype=torch.float16, 
-            use_safetensors=True, 
-            variant="fp16"
-        ).to("cuda")
-    elif model_name == "stabilityai/stable-diffusion-3-medium-diffusers":
-        pipeline = StableDiffusion3Pipeline.from_pretrained(
-            model_name, 
-            torch_dtype=torch.float16
-        ).to("cuda")
-    elif model_name == "stabilityai/stable-diffusion-2":
-        scheduler = EulerDiscreteScheduler.from_pretrained(model_name, subfolder="scheduler")
-        pipeline = StableDiffusionPipeline.from_pretrained(
-            model_name, 
-            scheduler=scheduler, 
-            torch_dtype=torch.float16
+    elif model_name == "sinteticoXL_Prude":
+        pipeline = StableDiffusionXLPipeline.from_single_file(
+            "https://huggingface.co/lucianosb/sinteticoXL-models/blob/main/sinteticoXL_prude_v1dot2.safetensors",
+            torch_dtype=torch.float16,
+            variant="fp16",
+            use_safetensors=True,
         ).to("cuda")
     else:
         raise ValueError("Unknown model name")
     return pipeline
 
 # Initialize the default model
-default_model = "stabilityai/stable-diffusion-3-medium-diffusers"
+default_model = "sinteticoXL"
 pipeline_text2image = load_model(default_model)
 
 @spaces.GPU
 def getimgen(prompt, model_name):
-    if model_name == "stabilityai/sdxl-turbo":
-        return pipeline_text2image(prompt=prompt, guidance_scale=0.0, num_inference_steps=2).images[0]
-    elif model_name == "runwayml/stable-diffusion-v1-5":
-        return pipeline_text2image(prompt).images[0]
-    elif model_name == "ByteDance/SDXL-Lightning":
-        return pipeline_text2image(prompt, num_inference_steps=4, guidance_scale=0).images[0]
-    elif model_name == "segmind/SSD-1B":
-        neg_prompt = "ugly, blurry, poor quality"
-        return pipeline_text2image(prompt=prompt, negative_prompt=neg_prompt).images[0]
-    elif model_name == "stabilityai/stable-diffusion-3-medium-diffusers":
-        return pipeline_text2image(prompt=prompt, negative_prompt="", num_inference_steps=28, guidance_scale=7.0).images[0]
-    elif model_name == "stabilityai/stable-diffusion-2":
-        return pipeline_text2image(prompt=prompt).images[0]
+    if model_name == "sinteticoXL":
+        return pipeline_text2image(prompt=prompt, guidance_scale=6.0, num_inference_steps=20).images[0]
+    elif model_name == "sinteticoXL_Prude":
+        return pipeline_text2image(prompt=prompt, guidance_scale=6.0, num_inference_steps=20).images[0]
 
 blip_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", torch_dtype=torch.float16).to("cuda")
@@ -181,16 +144,12 @@ This demo provides an insightful look into how current text-to-image models hand
     model_dropdown = gr.Dropdown(
         label="Choose a model", 
         choices=[
-            "stabilityai/stable-diffusion-3-medium-diffusers",
-            "stabilityai/sdxl-turbo", 
-            "ByteDance/SDXL-Lightning",
-            "stabilityai/stable-diffusion-2",
-            "runwayml/stable-diffusion-v1-5", 
-            "segmind/SSD-1B"
+            "sinteticoXL",
+            "sinteticoXL_Prude"
         ], 
         value=default_model
     )
-    prompt = gr.Textbox(label="Enter the Prompt", value = "photo of a doctor in india, detailed, 8k, sharp, high quality, good lighting")
+    prompt = gr.Textbox(label="Enter the Prompt", value = "photo of a beautiful Brazilian woman, high quality, good lighting")
     gallery = gr.Gallery(
         label="Generated images", 
         show_label=False,