Initial release

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sdxl1.png filter=lfs diff=lfs merge=lfs -text
+sdxl2.png filter=lfs diff=lfs merge=lfs -text
+sdxl3.png filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1764209071

README.md

@@ -0,0 +1,51 @@
+# OBS-Diff Structured Pruning for Stable Diffusion-xl-base-1.0 
+
+
+![](sdxl1.png)
+![](sdxl2.png)
+![](sdxl3.png)
+### Pruned UNet Variants
+| Sparsity (%) | 0 (Dense) | 10 | 15 | 20 | 25 | 30 |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: |
+| **Params (B)** | 2.57 | 2.35 | 2.24 | 2.13 | 2.02 | 1.91 |
+
+### How to use the pruned model
+
+1. Download the base model (SDXL) from [huggingface](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) or ModelScope.
+
+2. Download the pruned weights (.pth files) and use `torch.load` to replace the original UNet in the pipeline.
+
+3. Run inference using the code below.
+
+``` python
+import os
+import torch
+from diffusers import DiffusionPipeline
+from PIL import Image
+
+
+# 1. Load the base SDXL model
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
+
+# 2. Swap the original UNet with the pruned UNet checkpoint
+# Note: Ensure the path points to your downloaded .pth file
+pruned_unet_path = "/path/to/sparsity_30/unet_pruned.pth"
+pipe.unet = torch.load(pruned_unet_path, weights_only=False)
+pipe = pipe.to("cuda")
+
+total_params = sum(p.numel() for p in pipe.unet.parameters())
+print(f"Total UNet parameters: {total_params / 1e6:.2f} M")
+
+image = pipe(
+    prompt="A ship sailing through a sea of clouds, golden hour, impasto oil painting, brush strokes visible, dreamlike atmosphere.",
+    negative_prompt=None,
+    height=1024,
+    width=1024,
+    num_inference_steps=30,
+    guidance_scale=7.0,
+    generator=torch.Generator("cuda").manual_seed(42)
+).images[0]
+
+image.save("output_pruned.png")
+
+```

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-image-synthesis"}

sparsity_10/unet_pruned.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835b4bd42874ebdf9bfe41d69ac0a35f30a7ee062a0cb4f1341723883f3e795a
+size 4699003163

sparsity_15/unet_pruned.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab994c033322639a085f30de037a2a10478fd1bdf3743a8ab608ce5e4ac7c223
+size 4475458027

sparsity_20/unet_pruned.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c42b24f50227134ac7c2970aef3a0d9502dcdc95fd2f2176f975c22cf019ba
+size 4262071263

sparsity_25/unet_pruned.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a061c65239480e465abe45122bff07b0515de529e7d957bee0f65af0f1a9b4e6
+size 4048685023

sparsity_30/unet_pruned.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e15fc895c2c251dc2ef9ad2691c7f2428c5164b144290131b13c44beb58f851
+size 3825140703