first commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+spiderman.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,111 @@
+
+---
+license: openrail++
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+inference: false
+---
+    
+# SDXL-controlnet: Depth
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with depth conditioning. You can find some example images in the following. 
+
+prompt: spiderman lecture, photorealistic
+![images_0)](./spiderman.png)
+
+## Usage
+
+Make sure to first install the libraries:
+
+```bash
+pip install accelerate transformers safetensors diffusers
+```
+
+And then we're ready to go:
+
+```python
+import torch
+import numpy as np
+from PIL import Image
+
+from transformers import DPTFeatureExtractor, DPTForDepthEstimation
+from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
+from diffusers.utils import load_image
+
+
+depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to("cuda")
+feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
+controlnet = ControlNetModel.from_pretrained(
+    "diffusers/controlnet-depth-sdxl-1.0",
+    variant="fp16",
+    use_safetensors=True,
+    torch_dtype=torch.float16,
+)
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    controlnet=controlnet,
+    vae=vae,
+    variant="fp16",
+    use_safetensors=True,
+    torch_dtype=torch.float16,
+)
+pipe.enable_model_cpu_offload()
+
+def get_depth_map(image):
+    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to("cuda")
+    with torch.no_grad(), torch.autocast("cuda"):
+        depth_map = depth_estimator(image).predicted_depth
+
+    depth_map = torch.nn.functional.interpolate(
+        depth_map.unsqueeze(1),
+        size=(1024, 1024),
+        mode="bicubic",
+        align_corners=False,
+    )
+    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
+    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
+    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
+    image = torch.cat([depth_map] * 3, dim=1)
+
+    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
+    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
+    return image
+
+
+prompt = "stormtrooper lecture, photorealistic"
+image = load_image("https://huggingface.co/lllyasviel/sd-controlnet-depth/resolve/main/images/stormtrooper.png")
+controlnet_conditioning_scale = 0.5  # recommended for good generalization
+
+depth_image = get_depth_map(image)
+
+images = pipe(
+    prompt, image=depth_image, num_inference_steps=30, controlnet_conditioning_scale=controlnet_conditioning_scale,
+).images
+images[0]
+
+images[0].save(f"stormtrooper.png")
+```
+
+For more details, check out the official documentation of [`StableDiffusionXLControlNetPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_sdxl).
+
+### Training
+
+Our training script was built on top of the official training script that we provide [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md). 
+
+#### Training data and Compute
+The model is trained on 3M image-text pairs from LAION-Aesthetics V2. The model is trained for 700 GPU hours on 80GB A100 GPUs.
+
+#### Batch size
+Data parallel with a single GPU batch size of 8 for a total batch size of 256.
+
+#### Hyper Parameters
+The constant learning rate of 1e-5.
+
+#### Mixed precision
+fp16

config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.20.0.dev0",
+  "_name_or_path": "valhalla/depth-2",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}