Feature: Added image reference support to D-Processor

app.py

@@ -1,7 +1,7 @@
 import sys
 import os
 
-# --- INYECCIÓN ATÓMICA REFORZADA (Línea 1) ---
+# --- INYECCIÓN ATÓMICA REFORZADA ---
 try:
     import huggingface_hub
     class MockHfFolder:
@@ -11,14 +11,11 @@ try:
         def save_token(token): pass
         @staticmethod
         def delete_token(): pass
-    
-    # Inyectamos en todos los niveles posibles para evitar ImportError
     huggingface_hub.HfFolder = MockHfFolder
     sys.modules["huggingface_hub.HfFolder"] = MockHfFolder
     setattr(huggingface_hub, "HfFolder", MockHfFolder)
 except: pass
 
-# Parche de Audio para Python 3.13
 try:
     import audioop_lts
     sys.modules["audioop"] = audioop_lts
@@ -29,7 +26,7 @@ except:
 
 import gradio as gr
 
-# --- SILENCIADOR DE API (Previene el cartel rojo) ---
+# --- SILENCIADOR DE API ---
 def fake_get_api_info(self, *args, **kwargs):
     return {"components": [], "endpoints": []}
 gr.Blocks.get_api_info = fake_get_api_info
@@ -47,16 +44,12 @@ LTX_MODEL  = "Lightricks/LTX-Video"
 LTX_NSFW_LORA = "Lora-Daddy/Ltx2.3-real-nudity-early-alpha-30k-steps"
 NEG_DEFAULT = "blurry, low quality, bad anatomy, deformed, ugly, watermark, text"
 
-def load_t2i(lora_id=None, lora_scale=1.0):
-    from diffusers import StableDiffusionXLPipeline
-    pipe = StableDiffusionXLPipeline.from_pretrained(
+def load_t2i(is_img2img=False):
+    from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline
+    cls = StableDiffusionXLImg2ImgPipeline if is_img2img else StableDiffusionXLPipeline
+    pipe = cls.from_pretrained(
         BASE_MODEL, torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
     )
-    if lora_id and len(lora_id.strip()) > 5:
-        try:
-            pipe.load_lora_weights(lora_id.strip())
-            pipe.fuse_lora(lora_scale=lora_scale)
-        except: pass
     return pipe
 
 def load_video():
@@ -68,11 +61,31 @@ def load_video():
     return pipe
 
 @spaces.GPU(duration=100)
-def generate_t2i(prompt, neg, lora_id, lora_scale, w, h):
-    pipe = load_t2i(lora_id, lora_scale).to("cuda")
-    img = pipe(prompt=prompt, negative_prompt=neg, num_inference_steps=30, 
-               guidance_scale=7.0, width=int(w), height=int(h), 
-               generator=torch.Generator("cuda").manual_seed(42)).images[0]
+def generate_t2i(prompt, neg, lora_id, lora_scale, w, h, init_img):
+    is_img2img = init_img is not None
+    pipe = load_t2i(is_img2img).to("cuda")
+    
+    if lora_id and len(lora_id.strip()) > 5:
+        try:
+            pipe.load_lora_weights(lora_id.strip())
+            pipe.fuse_lora(lora_scale=lora_scale)
+        except: pass
+
+    kwargs = {
+        "prompt": prompt, "negative_prompt": neg, "num_inference_steps": 30, 
+        "guidance_scale": 7.0, "generator": torch.Generator("cuda").manual_seed(42)
+    }
+    
+    if is_img2img:
+        if isinstance(init_img, dict):
+            init_img = init_img["composite"] if "composite" in init_image else init_img["background"]
+        kwargs["image"] = Image.fromarray(init_img).convert("RGB").resize((int(w), int(h)))
+        kwargs["strength"] = 0.6 # Balance entre original y prompt
+    else:
+        kwargs["width"] = int(w)
+        kwargs["height"] = int(h)
+
+    img = pipe(**kwargs).images[0]
     return img
 
 @spaces.GPU(duration=200)
@@ -95,10 +108,11 @@ def generate_video(prompt, init_image, lora_scale):
 with gr.Blocks(title="Image Utility v2.1") as demo:
     gr.HTML("<h1 style='text-align:center;'>🛠 Image Processing Utility v2.1.4</h1>")
     with gr.Tabs():
-        with gr.Tab("D-Processor (T2I)"):
+        with gr.Tab("D-Processor (Image/T2I)"):
             with gr.Row():
                 with gr.Column():
                     t2i_p = gr.Textbox(label="Input Data String", lines=3)
+                    t2i_img = gr.Image(label="Base Reference (Optional)", type="numpy", sources=["upload", "clipboard"])
                     t2i_n = gr.Textbox(label="Excluded Data", value=NEG_DEFAULT)
                     t2i_lora = gr.Textbox(label="Extension ID")
                     t2i_ls = gr.Slider(0, 1.5, 0.8, label="Extension Weight")
@@ -107,7 +121,7 @@ with gr.Blocks(title="Image Utility v2.1") as demo:
                         t2i_h = gr.Slider(512, 1024, 1024, step=64, label="Y-Axis")
                     t2i_btn = gr.Button("Execute Process", variant="primary")
                 t2i_out = gr.Image(label="Output Preview")
-            t2i_btn.click(generate_t2i, [t2i_p, t2i_n, t2i_lora, t2i_ls, t2i_w, t2i_h], t2i_out)
+            t2i_btn.click(generate_t2i, [t2i_p, t2i_n, t2i_lora, t2i_ls, t2i_w, t2i_h, t2i_img], t2i_out)
 
         with gr.Tab("M-Sequence (Video)"):
             with gr.Row():