Initial release of OBS-Diff-SD3.5-Large

.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
+sd3-5-1.png filter=lfs diff=lfs merge=lfs -text
+sd3-5-2.png filter=lfs diff=lfs merge=lfs -text
+sd3-5-3.png filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1764209133

README.md

@@ -0,0 +1,52 @@
+# OBS-Diff Structured Pruning for Stable Diffusion 3.5-Large
+
+
+![](sd3-5-2.png)
+![](sd3-5-1.png)
+![](sd3-5-3.png)
+
+### Pruned Transformer Variants
+| Sparsity (%) | 0 (Dense) |  15 | 20 | 25 | 30 |
+| :--- | :---: | :---: |  :---: | :---: | :---: |
+| **Params (B)** | 8.06 | 7.28 | 7.02 | 6.76 | 6.54 |
+
+### How to use the pruned model
+
+1. Download the base model (SD3.5-Large) from [huggingface](https://huggingface.co/stabilityai/stable-diffusion-3.5-large) or ModelScope.
+
+2. Download the pruned weights (.pth files) and use `torch.load` to replace the original Transformer in the pipeline.
+
+3. Run inference using the code below.
+
+``` python
+import os
+import torch
+from diffusers import StableDiffusion3Pipeline
+from PIL import Image
+
+
+# 1. Load the base SD3.5-Large model
+pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.float16)
+
+# 2. Swap the original Transformer with the pruned Transformer checkpoint
+# Note: Ensure the path points to your downloaded .pth file
+pruned_transformer_path = "/path/to/sparsity_30/pruned_model.pth"
+pipe.transformer = torch.load(pruned_transformer_path, weights_only=False)
+pipe = pipe.to("cuda")
+
+total_params = sum(p.numel() for p in pipe.transformer.parameters())
+print(f"Total Transformer parameters: {total_params / 1e6:.2f} M")
+
+image = pipe(
+    prompt="photo of a delicious hamburger with fries and a coke on a wooden table, professional food photography, bokeh",
+    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_15/pruned_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f04450cac3dc284da522cd8698954d0ad3ad32e9cacdf61ed6d8f4f187104d
+size 14733084213

sparsity_20/pruned_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987eeee4543263a86224d03beb1bfddae5e0c5cf8d6556b5060a850c3a8dcc94
+size 14212550541

sparsity_25/pruned_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036bf191b9b689bbb2d666ea84aa76f7fbec5c4dce3775143753c47ca331c162
+size 13692717381

sparsity_30/pruned_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898b9c868ba0f8d64b018fac8e5e027afa5d3e1085a9f6d4b0c5261a8376b4af
+size 13262563645