Update README.md with the new API (#2)

- Update README.md with the new API (59496942a4509399e19931b26892e1d50ed016ea)


Co-authored-by: Multimodal AI art <[email protected]>

README.md

@@ -24,29 +24,23 @@ Please raise any concerns you may have.
 
 ```python
 # !pip install diffusers
-from diffusers import DiffusionPipeline
+from diffusers import LDMTextToImagePipeline
 import PIL.Image
 import numpy as np
 
-model_id = "CompVis/ldm-text2im-large-256q"
+model_id = "CompVis/ldm-text2im-large-256"
 
 # load model and scheduler
-ldm = DiffusionPipeline.from_pretrained(model_id)
+ldm = LDMTextToImagePipeline.from_pretrained(model_id)
 
 # run pipeline in inference (sample random noise and denoise)
 prompt = "A painting of a squirrel eating a burger"
-image = ldm([prompt])
+images = ldm([prompt], num_inference_steps=50, eta=0.3, guidance_scale=0.6, batch_size=1)["sample"]
 
-# process image to PIL
-image_processed = image.cpu().permute(0, 2, 3, 1)
-image_processed = (image_processed + 1.0) * 127.5
-image_processed = image_processed.numpy().astype(np.uint8)
-image_pil = PIL.Image.fromarray(image_processed[0])
-
-# save image
-image_pil.save("test.png")
+# save images
+for idx, image in enumerate(images):
+    image.save(f"squirrel-{idx}.png")
 ```
 
-## Samples
-
-TODO ...
+## Demo
+[Hugging Face Spaces](https://huggingface.co/spaces/CompVis/ldm-text2im-large-256-diffusers)