Update README.md

README.md

@@ -29,7 +29,7 @@ The authors call this procedure "consistency distillation (CD)".
 Consistency models can also be trained from scratch to generate clean images from a noisy image and timestep, which the authors call "consistency training (CT)".
 
 This model is a `diffusers`-compatible version of the [cd_imagenet64_lpips.pt](https://github.com/openai/consistency_models#pre-trained-models) checkpont from the [original code and model release](https://github.com/openai/consistency_models).
-This model was distilled from an [EDM model](https://arxiv.org/pdf/2206.00364.pdf) trained on the ImageNet 64x64 dataset, using [LPIPS](https://richzhang.github.io/PerceptualSimilarity/) as the measure of closeness.
+This model was distilled (via consistency distillation (CD)) from an [EDM model](https://arxiv.org/pdf/2206.00364.pdf) trained on the ImageNet 64x64 dataset, using [LPIPS](https://richzhang.github.io/PerceptualSimilarity/) as the measure of closeness.
 See the [original model card](https://github.com/openai/consistency_models/blob/main/model-card.md) for more information.
 
 ## Download
@@ -48,7 +48,7 @@ pipe = ConsistencyModelPipeline.from_pretrained("dg845/diffusers-cd_imagenet64_l
 
 The original model checkpoint can be used with the [original consistency models codebase](https://github.com/openai/consistency_models).
 
-Here is an example of using the `diffusers-cd_imagenet64_lpips` checkpoint with `diffusers`:
+Here is an example of using the `cd_imagenet64_lpips` checkpoint with `diffusers`:
 
 ```python
 import torch
@@ -63,7 +63,7 @@ pipe.to(device)
 
 # Onestep Sampling
 image = pipe(num_inference_steps=1).images[0]
-image.save("consistency_model_onestep_sample.png")
+image.save("cd_imagenet64_lpips_onestep_sample.png")
 
 # Onestep sampling, class-conditional image generation
 # ImageNet-64 class label 145 corresponds to king penguins