Duplicate from diffusers/controlnet-canny-sdxl-1.0

Co-authored-by: Will Berman <williamberman@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,41 @@
+*.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
+out_bird.png filter=lfs diff=lfs merge=lfs -text
+out_couple.png filter=lfs diff=lfs merge=lfs -text
+out_room.png filter=lfs diff=lfs merge=lfs -text
+out_tornado.png filter=lfs diff=lfs merge=lfs -text
+out_women.png filter=lfs diff=lfs merge=lfs -text
+out_hug_lab_7.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,107 @@
+---
+license: openrail++
+base_model: runwayml/stable-diffusion-v1-5
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+inference: false
+duplicated_from: diffusers/controlnet-canny-sdxl-1.0
+---
+    
+# SDXL-controlnet: Canny
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with canny conditioning. You can find some example images in the following. 
+
+prompt: a couple watching a romantic sunset, 4k photo
+![images_0)](./out_couple.png)
+
+prompt: ultrarealistic shot of a furry blue bird
+![images_1)](./out_bird.png)
+
+prompt: a woman, close up, detailed, beautiful, street photography, photorealistic, detailed, Kodak ektar 100, natural, candid shot
+![images_2)](./out_women.png)
+
+prompt: Cinematic, neoclassical table in the living room, cinematic, contour, lighting, highly detailed, winter, golden hour
+![images_3)](./out_room.png)
+
+prompt: a tornado hitting grass field, 1980's film grain. overcast, muted colors.
+![images_0)](./out_tornado.png)
+
+## Usage
+
+Make sure to first install the libraries:
+
+```bash
+pip install accelerate transformers safetensors opencv-python diffusers
+```
+
+And then we're ready to go:
+
+```python
+from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
+from diffusers.utils import load_image
+from PIL import Image
+import torch
+import numpy as np
+import cv2
+
+prompt = "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"
+negative_prompt = 'low quality, bad quality, sketches'
+
+image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
+
+controlnet_conditioning_scale = 0.5  # recommended for good generalization
+
+controlnet = ControlNetModel.from_pretrained(
+    "diffusers/controlnet-canny-sdxl-1.0",
+    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,
+    torch_dtype=torch.float16,
+)
+pipe.enable_model_cpu_offload()
+
+image = np.array(image)
+image = cv2.Canny(image, 100, 200)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+image = Image.fromarray(image)
+
+images = pipe(
+    prompt, negative_prompt=negative_prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale,
+    ).images
+
+images[0].save(f"hug_lab.png")
+```
+
+![images_10)](./out_hug_lab_7.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
+This checkpoint was first trained for 20,000 steps on laion 6a resized to a max minimum dimension of 384. 
+It was then further trained for 20,000 steps on laion 6a resized to a max minimum dimension of 1024 and 
+then filtered to contain only minimum 1024 images. We found the further high resolution finetuning was 
+necessary for image quality.
+
+#### Compute
+one 8xA100 machine
+
+#### Batch size
+Data parallel with a single gpu batch size of 8 for a total batch size of 64.
+
+#### Hyper Parameters
+Constant learning rate of 1e-4 scaled by batch size for total learning rate of 64e-4
+
+#### Mixed precision
+fp16

config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.20.0.dev0",
+  "_name_or_path": "../controlnet-1-0-canny/checkpoint-20000/controlnet",
+  "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.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982e12f72cb41031c060de08a5d78ff6912e9b02c6ad91fc480f05a72cad10cb
+size 5004438321

diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42da57d6e2fd6ec786ccfea1cf1a06d2c1d91b2d8a14c7de3a67553b10b2948
+size 2502401039

diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e7d3921058a442cc80430d1ec8847f42599c705e2451c95e77cf4dcf8d6c25
+size 2502139136

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea99040544a999f814fd854575a3aee069a005d026864c8d321b82576706a221
+size 5004167864