Update README.md

README.md

@@ -4,8 +4,7 @@ tags:
 - stable-diffusion
 - stable-diffusion-diffusers
 - text-to-image
-datasets:
-  - ChristophSchuhmann/improved_aesthetics_6.5plus
+- core-ml
 pipeline_tag: text-to-image
 extra_gated_prompt: >-
   This model is open access and available to all, with a CreativeML OpenRAIL-M
@@ -33,30 +32,27 @@ extra_gated_heading: Please read the LICENSE to access this model
 
 ---
 
-# BK-SDM Model Card (with Palettized Core ML Weights)
-Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining. Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
-
-This Model Card contains palettized Core ML weights for iOS 17 or macOS 14, for the following models: BK-SDM-{[**Base-2M**](https://huggingface.co/nota-ai/bk-sdm-base-2m), [**Small-2M**](https://huggingface.co/nota-ai/bk-sdm-small-2m) and [**Tiny-2M**](https://huggingface.co/nota-ai/bk-sdm-tiny-2m)}. These models were generated using [Apple’s repository](https://github.com/apple/ml-stable-diffusion) which has [ASCL](https://github.com/apple/ml-stable-diffusion/blob/main/LICENSE.md).
+# Palettized Core ML Weights for BK-SDMs
+For deployment on iOS 17 or macOS 14, this model card introduces palettized Core ML weights of BK-SDM-{[**Base-2M**](https://huggingface.co/nota-ai/bk-sdm-base-2m), [**Small-2M**](https://huggingface.co/nota-ai/bk-sdm-small-2m) and [**Tiny-2M**](https://huggingface.co/nota-ai/bk-sdm-tiny-2m)}. These weights were generated using [Apple’s repository](https://github.com/apple/ml-stable-diffusion) which has [ASCL](https://github.com/apple/ml-stable-diffusion/blob/main/LICENSE.md).
+- Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining. Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
+- More information about BK-SDMs: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
 
 A demo to use coreml Stable Diffusion weights can be found [here](https://github.com/huggingface/swift-coreml-diffusers).
 
-- **Resources for more information**: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
-
-## Performance comparison
 
-We have compared BK-SDM to [Apple's Stable Diffusion v1.4 palettized](https://huggingface.co/apple/coreml-stable-diffusion-1-4-palettized), and to [OFA-Sys' Small Stable Diffusion v0](https://huggingface.co/pcuenq/coreml-small-stable-diffusion-v0).
+## Deployment Results
 
 | Base Model Name      | Pipeline Size | Quantization Type                                                                 | Attention Implementation |
 |----------------------|---------------|-----------------------------------------------------------------------------------|--------------------------|
-| BK-SDM-Base-2M       | 1.48GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
-| BK-SDM-Small-2M      | 1.44GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
-| BK-SDM-Tiny-2M       | 1.43GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
-| Small Stable Diffusion v0 | 3.28GB  | None                                                                              | split_einsum            |
-| Stable Diffusion v1.4 | 1.57GB       | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
-
+| [BK-SDM-Base-2M](https://huggingface.co/nota-ai/bk-sdm-base-2m)  (Ours)       | 1.48GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
+| [BK-SDM-Small-2M](https://huggingface.co/nota-ai/bk-sdm-small-2m) (Ours)      | 1.44GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
+| [BK-SDM-Tiny-2M](https://huggingface.co/nota-ai/bk-sdm-tiny-2m) (Ours)       | 1.43GB        | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
+| [OFA-Sys' Small Stable Diffusion v0](https://huggingface.co/pcuenq/coreml-small-stable-diffusion-v0) | 3.28GB  | None                                                                              | split_einsum            |
+| [Apple's Stable Diffusion v1.4, Palettized](https://huggingface.co/apple/coreml-stable-diffusion-1-4-palettized) | 1.57GB       | [Palettized](https://coremltools.readme.io/docs/palettization-overview)            | split_einsum_v2         |
 
 <img src="https://huggingface.co/nota-ai/coreml-bk-sdm/resolve/main/assets/speed_comparison.gif">
 
+
 ## Compression Method 
 
 ### U-Net Architecture