File size: 11,990 Bytes
b0afe49 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "54f1a5b8-ed8b-4add-83a0-fa40732f80cc",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/root/miniconda3/envs/control/lib/python3.8/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"logging improved.\n",
"Enabled sliced_attention.\n",
"No module 'xformers'. Proceeding without it.\n",
"ControlInpaintLDM: Running in eps-prediction mode\n",
"DiffusionWrapper has 859.52 M params.\n",
"making attention of type 'vanilla' with 512 in_channels\n",
"Working with z of shape (1, 4, 32, 32) = 4096 dimensions.\n",
"making attention of type 'vanilla' with 512 in_channels\n",
"Loaded model config from [models/cldm_v15-mask.yaml]\n",
"Loaded state_dict from [/storage/ckpts15/c-20999.ckpt]\n"
]
}
],
"source": [
"from share import *\n",
"import config\n",
"\n",
"import einops\n",
"import gradio as gr\n",
"import numpy as np\n",
"import torch\n",
"import random\n",
"\n",
"from pytorch_lightning import seed_everything\n",
"from annotator.util import resize_image, HWC3\n",
"from cldm.model import create_model, load_state_dict\n",
"from cldm.ddim_hacked import DDIMSampler\n",
"\n",
"\n",
"model = create_model('models/cldm_v15-mask.yaml').cpu()\n",
"model.load_state_dict(load_state_dict('/storage/ckpts15/c-20999.ckpt', location='cuda'))\n",
"model = model.cuda()\n",
"ddim_sampler = DDIMSampler(model)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1ca4b664-22b5-4007-a663-696bbffa5d0a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Automatic pdb calling has been turned ON\n"
]
}
],
"source": [
"%pdb on"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bfbe23ec-793b-4f0c-a312-9f67177b8b43",
"metadata": {},
"outputs": [],
"source": [
"def process(ref_image, control_img, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta):\n",
" with torch.no_grad():\n",
" ref = resize_image(HWC3(ref_image), image_resolution)\n",
" H, W, C = ref.shape\n",
" \n",
" control = resize_image(HWC3(control_img), image_resolution)\n",
"\n",
" control = torch.from_numpy(np.array(control).astype(np.float32)).cuda() / 255.0\n",
" control = torch.stack([control for _ in range(num_samples)], dim=0)\n",
" control = einops.rearrange(control, 'b h w c -> b c h w').clone()\n",
" \n",
" ref = torch.from_numpy(np.array(ref).astype(np.float32)).cuda() / 255.0\n",
" ref = torch.stack([ref for _ in range(num_samples)], dim=0)\n",
" ref = einops.rearrange(ref, 'b h w c -> b c h w').clone()\n",
" \n",
" if seed == -1:\n",
" seed = random.randint(0, 65535)\n",
" seed_everything(seed)\n",
"\n",
" if config.save_memory:\n",
" model.low_vram_shift(is_diffusing=False)\n",
"\n",
" cond = {\"c_concat\": [control], \"c_crossattn\": [model.get_learned_conditioning(ref * num_samples)]}\n",
" #un_cond = {\"c_concat\": None if guess_mode else [control], \"c_crossattn\": [model.get_learned_conditioning([c] * num_samples)]}\n",
" shape = (4, H // 8, W // 8)\n",
"\n",
" if config.save_memory:\n",
" model.low_vram_shift(is_diffusing=True)\n",
"\n",
" model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13) # Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01\n",
" samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,\n",
" shape, cond, verbose=False, eta=eta,\n",
" unconditional_guidance_scale=1,\n",
" unconditional_conditioning=None)\n",
"\n",
" if config.save_memory:\n",
" model.low_vram_shift(is_diffusing=False)\n",
"\n",
" x_samples = model.decode_first_stage(samples)\n",
" x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)\n",
"\n",
" results = [x_samples[i] for i in range(num_samples)]\n",
" return [255 - detected_map] + results"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "389293fb-0b9e-4a7c-9b49-e6e13af53143",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7860\n",
"Running on public URL: https://af551707-d6f9-4083.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"https://af551707-d6f9-4083.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Global seed set to 1646781339\n",
"Traceback (most recent call last):\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/gradio/routes.py\", line 337, in run_predict\n",
" output = await app.get_blocks().process_api(\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/gradio/blocks.py\", line 1015, in process_api\n",
" result = await self.call_function(\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/gradio/blocks.py\", line 833, in call_function\n",
" prediction = await anyio.to_thread.run_sync(\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/anyio/to_thread.py\", line 31, in run_sync\n",
" return await get_asynclib().run_sync_in_worker_thread(\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/anyio/_backends/_asyncio.py\", line 937, in run_sync_in_worker_thread\n",
" return await future\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/anyio/_backends/_asyncio.py\", line 867, in run\n",
" result = context.run(func, *args)\n",
" File \"/tmp/ipykernel_2934/284040618.py\", line 23, in process\n",
" cond = {\"c_concat\": [control], \"c_crossattn\": [model.get_learned_conditioning(ref * num_samples)]}\n",
" File \"/notebooks/ControlNet/ldm/models/diffusion/ddpm.py\", line 667, in get_learned_conditioning\n",
" c = self.cond_stage_model.encode(c)\n",
" File \"/notebooks/ControlNet/ldm/modules/encoders/modules.py\", line 169, in encode\n",
" return self(image)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n",
" return forward_call(*input, **kwargs)\n",
" File \"/notebooks/ControlNet/ldm/modules/encoders/modules.py\", line 160, in forward\n",
" outputs = self.transformer(pixel_values=image)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n",
" return forward_call(*input, **kwargs)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py\", line 834, in forward\n",
" return self.vision_model(\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n",
" return forward_call(*input, **kwargs)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py\", line 765, in forward\n",
" hidden_states = self.embeddings(pixel_values)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n",
" return forward_call(*input, **kwargs)\n",
" File \"/root/miniconda3/envs/control/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py\", line 138, in forward\n",
" embeddings = embeddings + self.position_embedding(self.position_ids)\n",
"RuntimeError: The size of tensor a (1801) must match the size of tensor b (257) at non-singleton dimension 1\n"
]
}
],
"source": [
"block = gr.Blocks().queue()\n",
"with block:\n",
" with gr.Row():\n",
" gr.Markdown(\"## Control Stable Diffusion with Canny Edge Maps\")\n",
" with gr.Row():\n",
" with gr.Column():\n",
" control_image = gr.Image(label=\"img mask\", source='upload', type=\"numpy\")\n",
" ref_image = gr.Image(label=\"ref image\", source='upload', type=\"numpy\")\n",
" run_button = gr.Button(label=\"Run\")\n",
" with gr.Accordion(\"Advanced options\", open=False):\n",
" num_samples = gr.Slider(label=\"Images\", minimum=1, maximum=12, value=1, step=1)\n",
" image_resolution = gr.Slider(label=\"Image Resolution\", minimum=256, maximum=768, value=512, step=64)\n",
" strength = gr.Slider(label=\"Control Strength\", minimum=0.0, maximum=2.0, value=1.0, step=0.01)\n",
" guess_mode = gr.Checkbox(label='Guess Mode', value=False)\n",
" ddim_steps = gr.Slider(label=\"Steps\", minimum=1, maximum=100, value=20, step=1)\n",
" scale = gr.Slider(label=\"Guidance Scale\", minimum=0.1, maximum=30.0, value=9.0, step=0.1)\n",
" seed = gr.Slider(label=\"Seed\", minimum=-1, maximum=2147483647, step=1, randomize=True)\n",
" eta = gr.Number(label=\"eta (DDIM)\", value=0.0)\n",
" \n",
" with gr.Column():\n",
" result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=\"gallery\").style(grid=2, height='auto')\n",
" ips = [ref_image, control_image, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta]\n",
" run_button.click(fn=process, inputs=ips, outputs=[result_gallery])\n",
"\n",
"\n",
"block.launch(debug=True, share=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5142b6dd-0a56-4779-82dc-ff786986535d",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "b8f00ec0-2a16-4e73-8d69-859ca1c665df",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "controlnet",
"language": "python",
"name": "controlnet"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|