Duplicate from thibaud/controlnet-openpose-sdxl-1.0

Co-authored-by: Thib aud <thibaud@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.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_ballerina.png filter=lfs diff=lfs merge=lfs -text
+darth_vader_grid.png filter=lfs diff=lfs merge=lfs -text

OpenPoseXL2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4b928cb1e93748217900cb66d4135bf70d932d2924232f925910fad9e43a92
+size 5004167829

README.md

@@ -0,0 +1,99 @@
+---
+license: other
+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: OpenPose (v2)
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with OpenPose (v2) conditioning. You can find some example images in the following. 
+
+prompt: a ballerina, romantic sunset, 4k photo
+![images_0)](./screenshot_ballerina.png)
+
+
+### Comfy Workflow
+![images_0)](./out_ballerina.png)
+
+
+(Image is from ComfyUI, you can drag and drop in Comfy to use it as workflow)
+
+License: refers to the OpenPose's one.
+
+### Using in 🧨 diffusers
+
+First, install all the libraries:
+
+```bash
+pip install -q controlnet_aux transformers accelerate
+pip install -q git+https://github.com/huggingface/diffusers
+```
+
+Now, we're ready to make Darth Vader dance:
+
+```python
+from diffusers import AutoencoderKL, StableDiffusionXLControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
+import torch
+from controlnet_aux import OpenposeDetector
+from diffusers.utils import load_image
+
+
+# Compute openpose conditioning image.
+openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/person.png"
+)
+openpose_image = openpose(image)
+
+# Initialize ControlNet pipeline.
+controlnet = ControlNetModel.from_pretrained("thibaud/controlnet-openpose-sdxl-1.0", torch_dtype=torch.float16)
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float16
+)
+pipe.enable_model_cpu_offload()
+
+
+# Infer.
+prompt = "Darth vader dancing in a desert, high quality"
+negative_prompt = "low quality, bad quality"
+images = pipe(
+    prompt, 
+    negative_prompt=negative_prompt,
+    num_inference_steps=25,
+    num_images_per_prompt=4,
+    image=openpose_image.resize((1024, 1024)),
+    generator=torch.manual_seed(97),
+).images
+images[0]
+```
+
+Here are some gemerated examples:
+
+![](./darth_vader_grid.png)
+
+
+### Training
+
+Use of the training script by HF🤗 [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md). 
+
+#### Training data
+This checkpoint was first trained for 15,000 steps on laion 6a resized to a max minimum dimension of 768. 
+
+#### Compute
+one 1xA100 machine (Thanks a lot HF🤗 to provide the compute!)
+
+#### Batch size
+Data parallel with a single gpu batch size of 2 with gradient accumulation 8.
+
+#### Hyper Parameters
+Constant learning rate of 8e-5
+
+#### Mixed precision
+fp16

config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.20.0.dev0",
+  "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
+}

control-lora-openposeXL2-rank256.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afa079285bf9384eaf8f6322884cb4f24bbe405da490f91f5540d3bff585e75
+size 774423024

diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbc89bdf2c4176ec58c65b0dbd9106976eb6d784ea65c3c1fb9a3f3fb62f922
+size 5004438321