Update app.py

app.py

@@ -82,31 +82,180 @@ with torch.inference_mode():
     empty_latent = EmptyLatentImage()
 
 @spaces.GPU
-def generate_image(prompt, input_image, strength, progress=gr.Progress(track_tqdm=True)):
+def generate_image(prompt, input_image, lora_weight, guidance, downsampling_factor, weight, seed, width, height, batch_size, steps, progress=gr.Progress(track_tqdm=True)):
     try:
         with torch.inference_mode():
-            # Seu código de geração aqui
-            pass
+            # Codificar texto
+            cliptextencode = NODE_CLASS_MAPPINGS["CLIPTextEncode"]()
+            encoded_text = cliptextencode.encode(
+                text=prompt,
+                clip=dualcliploader_357[0]
+            )
+
+            # Carregar e processar imagem
+            loadimage = NODE_CLASS_MAPPINGS["LoadImage"]()
+            loaded_image = loadimage.load_image(image=input_image)
+
+            # Flux Guidance
+            fluxguidance = NODE_CLASS_MAPPINGS["FluxGuidance"]()
+            flux_guidance = fluxguidance.append(
+                guidance=guidance,
+                conditioning=encoded_text[0]
+            )
+
+            # Carregar LoRA
+            loraloadermodelonly = NODE_CLASS_MAPPINGS["LoraLoaderModelOnly"]()
+            lora_model = loraloadermodelonly.load_lora_model_only(
+                lora_name="models/lora/NFTNIK_FLUX.1[dev]_LoRA.safetensors",
+                strength_model=lora_weight,
+                model=stylemodelloader_441[0]
+            )
+
+            # Redux Advanced
+            reduxadvanced = NODE_CLASS_MAPPINGS["ReduxAdvanced"]()
+            redux_result = reduxadvanced.apply_stylemodel(
+                downsampling_factor=downsampling_factor,
+                downsampling_function="area",
+                mode="keep aspect ratio",
+                weight=weight,
+                conditioning=flux_guidance[0],
+                style_model=stylemodelloader_441[0],
+                image=loaded_image[0]
+            )
+
+            # Empty Latent
+            emptylatentimage = NODE_CLASS_MAPPINGS["EmptyLatentImage"]()
+            empty_latent = emptylatentimage.generate(
+                width=width,
+                height=height,
+                batch_size=batch_size
+            )
+
+            # KSampler
+            ksampler = NODE_CLASS_MAPPINGS["KSampler"]()
+            sampled = ksampler.sample(
+                seed=seed,
+                steps=steps,
+                cfg=1,
+                sampler_name="euler",
+                scheduler="simple",
+                denoise=1,
+                model=lora_model[0],
+                positive=redux_result[0],
+                negative=flux_guidance[0],
+                latent_image=empty_latent[0]
+            )
+
+            # Decodificar VAE
+            vaedecode = NODE_CLASS_MAPPINGS["VAEDecode"]()
+            decoded = vaedecode.decode(
+                samples=sampled[0],
+                vae=vaeloader_359[0]
+            )
+
+            # Salvar imagem
+            temp_filename = f"Flux_{random.randint(0, 99999)}.png"
+            temp_path = os.path.join(output_dir, temp_filename)
+            Image.fromarray((decoded[0] * 255).astype("uint8")).save(temp_path)
+
+            return temp_path
     except Exception as e:
         print(f"Erro ao gerar imagem: {str(e)}")
         return None
 
 # Interface Gradio
 with gr.Blocks() as app:
-    gr.Markdown("# Gerador de Imagens FLUX")
+    gr.Markdown("# FLUX Redux Image Generator")
+    
     with gr.Row():
         with gr.Column():
-            prompt_input = gr.Textbox(label="Prompt", placeholder="Digite seu prompt aqui...", lines=5)
-            input_image = gr.Image(label="Imagem de Entrada", type="filepath")
-            strength = gr.Slider(minimum=0, maximum=2, step=0.1, value=1.0, label="Força")
-            generate_btn = gr.Button("Gerar Imagem")
-
+            prompt_input = gr.Textbox(
+                label="Prompt",
+                placeholder="Enter your prompt here...",
+                lines=5
+            )
+            input_image = gr.Image(
+                label="Input Image",
+                type="filepath"
+            )
+            
+            with gr.Row():
+                with gr.Column():
+                    lora_weight = gr.Slider(
+                        minimum=0,
+                        maximum=2,
+                        step=0.1,
+                        value=0.6,
+                        label="LoRA Weight"
+                    )
+                    guidance = gr.Slider(
+                        minimum=0,
+                        maximum=20,
+                        step=0.1,
+                        value=3.5,
+                        label="Guidance"
+                    )
+                    downsampling_factor = gr.Slider(
+                        minimum=1,
+                        maximum=8,
+                        step=1,
+                        value=3,
+                        label="Downsampling Factor"
+                    )
+                    weight = gr.Slider(
+                        minimum=0,
+                        maximum=2,
+                        step=0.1,
+                        value=1.0,
+                        label="Model Weight"
+                    )
+                with gr.Column():
+                    seed = gr.Number(
+                        value=random.randint(1, 2**64),
+                        label="Seed",
+                        precision=0
+                    )
+                    width = gr.Number(
+                        value=1024,
+                        label="Width",
+                        precision=0
+                    )
+                    height = gr.Number(
+                        value=1024,
+                        label="Height",
+                        precision=0
+                    )
+                    batch_size = gr.Number(
+                        value=1,
+                        label="Batch Size",
+                        precision=0
+                    )
+                    steps = gr.Number(
+                        value=20,
+                        label="Steps",
+                        precision=0
+                    )
+            
+            generate_btn = gr.Button("Generate Image")
+        
         with gr.Column():
-            output_image = gr.Image(label="Imagem Gerada", type="filepath")
-
+            output_image = gr.Image(label="Generated Image", type="pil")
+    
     generate_btn.click(
         fn=generate_image,
-        inputs=[prompt_input, input_image, strength],
+        inputs=[
+            prompt_input,
+            input_image,
+            lora_weight,
+            guidance,
+            downsampling_factor,
+            weight,
+            seed,
+            width,
+            height,
+            batch_size,
+            steps
+        ],
         outputs=[output_image]
     )