add diffusers weights (#1)

- add weights (678355f2e2e45ab5a9413799f386ead2bff81aef)
- add readme (ce200773d085a919b55deed0eceaa12b1c4fd75a)
- update the readme (2c24837a61b85ab7ac2da90d0a9bc29323979dc8)
- up (1c503edc64ca10e37cd36a8f145961e1fd34e119)


Co-authored-by: YiYi Xu <[email protected]>

README.md

@@ -91,6 +91,45 @@ Which should give you an image like below:
 
 ![A girl sitting in a cafe](sample_result.png)
 
+### Using Controlnets in Diffusers
+
+Make sure you upgrade to the latest diffusers version: `pip install -U diffusers`. And then you can run:
+
+```python
+import torch
+from diffusers import StableDiffusion3ControlNetPipeline, SD3ControlNetModel
+from diffusers.utils import load_image
+
+controlnet = SD3ControlNetModel.from_pretrained("stabilityai/stable-diffusion-3.5-large-controlnet-depth", torch_dtype=torch.float16)
+pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-3.5-large",
+    controlnet=controlnet,
+    torch_dtype=torch.float16,
+).to("cuda")
+
+control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/marigold/marigold_einstein_lcm_depth.png")
+generator = torch.Generator(device="cpu").manual_seed(0)
+image = pipe(
+    prompt = "a photo of a man", 
+    control_image=control_image, 
+    guidance_scale=4.5,
+    num_inference_steps=40,
+    generator=generator,
+    max_sequence_length=77,
+).images[0]
+image.save('depth-8b.jpg')
+```
+
+You can use `image_gen_aux` to extract `depth_image`, which contains all the preprocessor required to use with diffusers pipelines. 
+
+```python
+# install image_gen_aux with: pip install git+https://github.com/huggingface/image_gen_aux.git
+from image_gen_aux import DepthPreprocessor
+image = load_image("path to image")
+
+depth_preprocessor = DepthPreprocessor.from_pretrained("depth-anything/Depth-Anything-V2-Large-hf").to("cuda")
+depth_image = depth_preprocessor(image, invert=True)[0].convert("RGB")
+```
 
 ### Preprocessing
 

config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "SD3ControlNetModel",
+  "_diffusers_version": "0.32.0.dev0",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 2048,
+  "dual_attention_layers": [],
+  "extra_conditioning_channels": 0,
+  "force_zeros_for_pooled_projection": false,
+  "in_channels": 16,
+  "joint_attention_dim": null,
+  "num_attention_heads": 38,
+  "num_layers": 19,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": null,
+  "pos_embed_type": null,
+  "qk_norm": null,
+  "sample_size": 128,
+  "use_pos_embed": false
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd54d6c670ebc864b459f251573bc0f9cb60f2adf644dbd4df4ffab6879b1a1
+size 8614110992