Update app.py

app.py

@@ -1,5 +1,4 @@
-from fastapi import FastAPI, UploadFile, File
-from pydantic import BaseModel
+from fastapi import FastAPI, UploadFile, File, Query
 from diffusers import StableDiffusionPipeline
 from huggingface_hub import hf_hub_download
 from fastapi.responses import StreamingResponse
@@ -10,52 +9,77 @@ import io
 app = FastAPI()
 
 MODEL_REPO = "ebraam1/interior-sd-models"
-MODEL_FILE = "Interior.safetensors"
+BASE_MODEL = "Interior.safetensors"
+LORA_FILE = "Interior_lora.safetensors"
 
-print("Downloading model file...")
-model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)
+# ---------- تحميل الموديل الأساسي ----------
+print("Downloading base model...")
+base_path = hf_hub_download(repo_id=MODEL_REPO, filename=BASE_MODEL)
 
-print("Loading model on CPU...")
+print("Loading base model on CPU...")
 pipe = StableDiffusionPipeline.from_single_file(
-    model_path,
+    base_path,
     torch_dtype=torch.float32,
     safety_checker=None,
     requires_safety_checker=False
 ).to("cpu")
 
+# ---------- تحميل الـ LoRA ودمجه ----------
+print("Downloading LoRA...")
+lora_path = hf_hub_download(repo_id=MODEL_REPO, filename=LORA_FILE)
+
+print("Loading LoRA...")
+pipe.load_lora_weights(lora_path)
+pipe.fuse_lora(lora_scale=1.0)  # القوة الكاملة للـ LoRA
+
+# تحسين الأداء (بدون تغيير الجدول الزمني)
 pipe.enable_attention_slicing()
 pipe.enable_vae_slicing()
 
-print("Model ready 🔥")
+print("Model ready 🔥 (Base + LoRA fused)")
 
-class Prompt(BaseModel):
-    prompt: str
-
-def to_bytes(img: Image.Image):
+# ---------- دوال مساعدة ----------
+def to_bytes(img: Image.Image) -> io.BytesIO:
     buf = io.BytesIO()
     img.save(buf, format="PNG")
     buf.seek(0)
     return buf
 
-@app.post("/txt2img")
-def generate(data: Prompt):
+# ---------- Text‑to‑Image (GET بسيط بباراميتر تيكست) ----------
+@app.get("/txt2img")
+def txt2img(
+    prompt: str = Query(..., description="الوصف اللي عايز تولده"),
+    steps: int = Query(8, ge=1, le=20),
+    guidance: float = Query(7.5, ge=1.0, le=20.0),
+    height: int = Query(512, ge=256, le=768),
+    width: int = Query(512, ge=256, le=768)
+):
     image = pipe(
-        data.prompt,
-        num_inference_steps=8,
-        guidance_scale=7.5,
-        height=512,
-        width=512
+        prompt=prompt,
+        num_inference_steps=steps,
+        guidance_scale=guidance,
+        height=height,
+        width=width
     ).images[0]
     return StreamingResponse(to_bytes(image), media_type="image/png")
 
+# ---------- Image‑to‑Image (POST مع رفع صورة + باراميترات) ----------
 @app.post("/img2img")
-async def img2img_api(file: UploadFile = File(...), prompt: str = ""):
-    img = Image.open(io.BytesIO(await file.read())).convert("RGB").resize((512, 512))
+async def img2img(
+    file: UploadFile = File(...),
+    prompt: str = Query(""),
+    steps: int = Query(8, ge=1, le=20),
+    guidance: float = Query(7.5, ge=1.0, le=20.0),
+    strength: float = Query(0.6, ge=0.0, le=1.0),
+    height: int = Query(512, ge=256, le=768),
+    width: int = Query(512, ge=256, le=768)
+):
+    img = Image.open(io.BytesIO(await file.read())).convert("RGB").resize((width, height))
     image = pipe(
         prompt=prompt,
         image=img,
-        strength=0.6,
-        num_inference_steps=8,
-        guidance_scale=7.5
+        strength=strength,
+        num_inference_steps=steps,
+        guidance_scale=guidance
     ).images[0]
     return StreamingResponse(to_bytes(image), media_type="image/png")