Update README.md

README.md

@@ -174,12 +174,10 @@ The dataset we trained our model on can be found here. We used 11 Renaissance po
 When launching training, a diffusion model checkpoint is generated epoch-wise only if the current loss is lower than the previous one. To avoid OOM and faster training, we used an A100 GPU in Google Colab.
 We fine-tuned the model on two different resolutions: 256x256 and 512x512. We only varied the batch size and number of epochs for fine-tuning with these two different resolutions. The best results were obtained with 512 x 512 pixels, 72 epochs, batch size of 1 and mixed precision set to True.
 
-Hardware: A100 GPUs
+Hardware: A100 GPU
 
 Optimizer: AdamW
 
-Gradient Accumulations: 2
-
 Batch: 1
 
 Learning rate: warmup to 0.0001 for 10,000 steps and then kept constant
@@ -300,12 +298,12 @@ my_base_model = keras_cv.models.StableDiffusion(img_width=512, img_height=512)
 ```
 ### 4. Load Weights from the h5 model which is hosted on Hugging Face:
 ```python
-my_base_model.diffusion_model.load_weights('/path/to/file/renaissance_model.h5')
+my_base_model.diffusion_model.load_weights(path/to/file/renaissance_model.h5)
 ```
 ### 5. Create a variable to hold the values of the to-be-generated image such as prompt, batch size, iterations, and seed
 ```python
 img = my_base_model.text_to_image(
-       prompt="A woman with an enigmatic smile against a dark background",
+       prompt=A woman with an enigmatic smile against a dark background,
        batch_size=1,  # How many images to generate at once
        num_steps=25,  # Number of iterations (controls image quality)
        seed=123,  # Set this to always get the same image from the same prompt