Duplicate from diffusers/controlnet-zoe-depth-sdxl-1.0

Co-authored-by: Suraj Patil <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,157 @@
+
+---
+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: Zoe-Depth
+
+These are ControlNet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with zoe depth conditioning. [Zoe-depth](https://github.com/isl-org/ZoeDepth) is an open-source SOTA depth estimation model which produces high-quality depth maps, which are better suited for conditioning.
+
+You can find some example images in the following. 
+
+![images_0)](./zoe-depth-example.png)
+
+![images_2](./zoe-megatron.png)
+
+![images_3](./photo-woman.png)
+
+## Usage
+
+Make sure first to install the libraries:
+
+```bash
+pip install accelerate transformers safetensors diffusers
+```
+
+And then setup the zoe-depth model
+
+```
+import torch
+import matplotlib
+import matplotlib.cm
+import numpy as np
+
+torch.hub.help("intel-isl/MiDaS", "DPT_BEiT_L_384", force_reload=True)  # Triggers fresh download of MiDaS repo
+model_zoe_n = torch.hub.load("isl-org/ZoeDepth", "ZoeD_NK", pretrained=True).eval()
+model_zoe_n = model_zoe_n.to("cuda")
+
+
+def colorize(value, vmin=None, vmax=None, cmap='gray_r', invalid_val=-99, invalid_mask=None, background_color=(128, 128, 128, 255), gamma_corrected=False, value_transform=None):
+    if isinstance(value, torch.Tensor):
+        value = value.detach().cpu().numpy()
+
+    value = value.squeeze()
+    if invalid_mask is None:
+        invalid_mask = value == invalid_val
+    mask = np.logical_not(invalid_mask)
+
+    # normalize
+    vmin = np.percentile(value[mask],2) if vmin is None else vmin
+    vmax = np.percentile(value[mask],85) if vmax is None else vmax
+    if vmin != vmax:
+        value = (value - vmin) / (vmax - vmin)  # vmin..vmax
+    else:
+        # Avoid 0-division
+        value = value * 0.
+
+    # squeeze last dim if it exists
+    # grey out the invalid values
+
+    value[invalid_mask] = np.nan
+    cmapper = matplotlib.cm.get_cmap(cmap)
+    if value_transform:
+        value = value_transform(value)
+        # value = value / value.max()
+    value = cmapper(value, bytes=True)  # (nxmx4)
+
+    # img = value[:, :, :]
+    img = value[...]
+    img[invalid_mask] = background_color
+
+    # gamma correction
+    img = img / 255
+    img = np.power(img, 2.2)
+    img = img * 255
+    img = img.astype(np.uint8)
+    img = Image.fromarray(img)
+    return img
+
+
+def get_zoe_depth_map(image):
+    with torch.autocast("cuda", enabled=True):
+        depth = model_zoe_n.infer_pil(image)
+    depth = colorize(depth, cmap="gray_r")
+    return depth
+```
+
+Now we're ready to go:
+
+```python
+import torch
+import numpy as np
+from PIL import Image
+
+from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
+from diffusers.utils import load_image
+
+controlnet = ControlNetModel.from_pretrained(
+  "diffusers/controlnet-zoe-depth-sdxl-1.0",
+  use_safetensors=True,
+  torch_dtype=torch.float16,
+).to("cuda")
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16).to("cuda")
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+  "stabilityai/stable-diffusion-xl-base-1.0",
+  controlnet=controlnet,
+  vae=vae,
+  variant="fp16",
+  use_safetensors=True,
+  torch_dtype=torch.float16,
+).to("cuda")
+pipe.enable_model_cpu_offload()
+
+
+prompt = "pixel-art margot robbie as barbie, in a coupé . low-res, blocky, pixel art style, 8-bit graphics"
+negative_prompt = "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic"
+image = load_image("https://media.vogue.fr/photos/62bf04b69a57673c725432f3/3:2/w_1793,h_1195,c_limit/rev-1-Barbie-InstaVert_High_Res_JPEG.jpeg")
+
+controlnet_conditioning_scale = 0.55
+
+depth_image = get_zoe_depth_map(image).resize((1088, 896))
+
+generator = torch.Generator("cuda").manual_seed(978364352)
+images = pipe(
+  prompt, image=depth_image, num_inference_steps=50, controlnet_conditioning_scale=controlnet_conditioning_scale, generator=generator
+).images
+images[0]
+
+images[0].save(f"pixel-barbie.png")
+```
+
+![images_1)](./barbie.png)
+
+To 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
+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/zoe-depth",
+  "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
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd9dad0c25b90a548f2598b575505884d9b535ad17f3e13b8a1701554200ecd
+size 2502139134