Update README.md

README.md

@@ -19,9 +19,42 @@ You can use the original Qwen-Image-Edit parameters.
 
 This model is `not yet` available for inference at JustLab.ai
 
-Note: this model has not been tested by Justlab.
-IMPORTANT: You should only use the `transformer` and `text_encoder` other directory files should be replaced with original Qwen-Image-Edit.
-The repo will be updated to v1 to fix this.
+Model tested: Working perfectly even with 20 steps.
+
+Sample script.
+
+```
+import os
+from PIL import Image
+import torch
+
+from diffusers import QwenImageEditPipeline
+
+model_path = "ovedrive/qwen-image-edit-4bit"
+pipeline = QwenImageEditPipeline.from_pretrained(model_path, torch_dtype=torch.bfloat16)
+print("pipeline loaded") # not true but whatever. do not move to cuda
+
+pipeline.set_progress_bar_config(disable=None)
+pipeline.enable_model_cpu_offload() #if you have enough VRAM remove this line for faster inference.
+image = Image.open("./example.png").convert("RGB")
+prompt = "Remove the lady head with white hair"
+inputs = {
+    "image": image,
+    "prompt": prompt,
+    "generator": torch.manual_seed(0),
+    "true_cfg_scale": 4.0,
+    "negative_prompt": " ",
+    "num_inference_steps": 20,
+}
+
+with torch.inference_mode():
+  output = pipeline(**inputs)
+
+output_image = output.images[0]
+output_image.save("output_image_edit.png")
+print("image saved at", os.path.abspath("output_image_edit.png"))
+```
+
 
 The original Qwen-Image attributions are included verbatim below.