├── LICENSE ├── NOTICE ├── README.md ├── dataset ├── testset.pkl ├── testset_instances.pkl ├── testset_layout.tar.gz ├── valset.pkl └── valset_layout.tar.gz ├── eval_iou.ipynb ├── figures ├── example_0.png ├── example_1.png ├── example_2.png ├── method.png ├── sample.png ├── step1.png ├── step2.png ├── step3.png ├── step3_.png ├── step4.png └── step4_.png ├── gradio_app.py ├── inference.ipynb ├── requirements.txt └── utils.py /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright (c) 2023-present NAVER Cloud Corp. 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- 1 | DenseDiffusion 2 | Copyright (c) 2023-present NAVER Cloud Corp. 3 | 4 | Licensed under the Apache License, Version 2.0 (the "License"); 5 | you may not use this file except in compliance with the License. 6 | You may obtain a copy of the License at 7 | 8 | http://www.apache.org/licenses/LICENSE-2.0 9 | 10 | Unless required by applicable law or agreed to in writing, software 11 | distributed under the License is distributed on an "AS IS" BASIS, 12 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | See the License for the specific language governing permissions and 14 | limitations under the License. 15 | 16 | -------------------------------------------------------------------------------------- 17 | 18 | This project contains subcomponents with separate copyright notices and license terms. 19 | Your use of the source code for these subcomponents is subject to the terms and conditions of the following licenses. 20 | 21 | ===== 22 | 23 | Multidiffusion Spatial Controls 24 | https://huggingface.co/spaces/weizmannscience/multidiffusion-region-based/tree/main 25 | 26 | 27 | https://huggingface.co/spaces/weizmannscience/multidiffusion-region-based 28 | 29 | Permission is hereby granted, free of charge, to any person obtaining a copy 30 | of this software and associated documentation files (the "Software"), to deal 31 | in the Software without restriction, including without limitation the rights 32 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 33 | copies of the Software, and to permit persons to whom the Software is 34 | furnished to do so, subject to the following conditions: 35 | 36 | The above copyright notice and this permission notice shall be included in 37 | all copies or substantial portions of the Software. 38 | 39 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 40 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 41 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 42 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 43 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 44 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN 45 | THE SOFTWARE. 46 | 47 | ===== 48 | 49 | huggingface/diffusers 50 | https://github.com/huggingface/diffusers 51 | 52 | 53 | # Licensed under the Apache License, Version 2.0 (the "License"); 54 | # you may not use this file except in compliance with the License. 55 | # You may obtain a copy of the License at 56 | # 57 | # http://www.apache.org/licenses/LICENSE-2.0 58 | # 59 | # Unless required by applicable law or agreed to in writing, software 60 | # distributed under the License is distributed on an "AS IS" BASIS, 61 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 62 | # See the License for the specific language governing permissions and 63 | # limitations under the License. 64 | 65 | ===== 66 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## Dense Text-to-Image Generation with Attention Modulation 2 | ### ICCV 2023 [[Paper](https://arxiv.org/abs/2308.12964)] [[Demo on HF 🤗](https://huggingface.co/spaces/naver-ai/DenseDiffusion)] [[Colab Demo](https://github.com/XandrChris/DenseDiffusionColab)]

3 | > #### Authors    [Yunji Kim](https://github.com/YunjiKim)1, [Jiyoung Lee](https://lee-jiyoung.github.io)1, [Jin-Hwa Kim](http://wityworks.com/)1, [Jung-Woo Ha](https://github.com/jungwoo-ha)1, [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/)2
         1NAVER AI Lab, 2Carnegie Mellon University 4 | 5 | > #### Abstract 6 | Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. 7 | To address this, we propose DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle such dense captions while offering control over the scene layout. 8 | We first analyze the relationship between generated images' layouts and the pre-trained model's intermediate attention maps. 9 | Next, we develop an attention modulation method that guides objects to appear in specific regions according to layout guidance. 10 | Without requiring additional fine-tuning or datasets, we improve image generation performance given dense captions regarding both automatic and human evaluation scores. 11 | In addition, we achieve similar-quality visual results with models specifically trained with layout conditions. 12 | 13 | 14 | > #### Method 15 |

16 | 17 |

18 |

19 | 20 |

21 | 22 | Our goal is to improve the text-to-image model's ability to reflect textual and spatial conditions without fine-tuning. 23 | We formally define our condition as a set of $N$ segments ${\lbrace(c_{n},m_{n})\rbrace}^{N}_{n=1}$, where each segment $(c_n,m_n)$ describes a single region. 24 | Here $c_n$ is a non-overlapping part of the full-text caption $c$, and $m_n$ denotes a binary map representing each region. Given the input conditions, we modulate attention maps of all attention layers on the fly so that the object described by $c_n$ can be generated in the corresponding region $m_n$. 25 | To maintain the pre-trained model's generation capacity, we design the modulation to consider original value range and each segment's area. 26 | 27 | 28 | > #### Examples 29 | 30 |

31 | 32 |

33 | 34 |

35 | 36 |

37 | 38 |

39 | 40 |

41 | 42 | 43 | ---- 44 | 45 | ### How to launch a web interface 46 | 47 | - Put your access token to Hugging Face Hub [here](./gradio_app.py#L77). 48 | 49 | - Run the Gradio app. 50 | ``` 51 | python gradio_app.py 52 | ``` 53 | 54 | 55 | ---- 56 | 57 | 58 | ### Getting Started 59 | 60 | - Create the image layout. 61 |

62 | 63 |

64 | 65 | - Label each segment with a text prompt. 66 |

67 | 68 |

69 | 70 | - Adjust the full text. The default full text is automatically concatenated from each segment's text. The default one works well, but refineing the full text will further improve the result. 71 |

72 | 73 |

74 | 75 | - Check the generated images, and tune the hyperparameters if needed.
76 | wc : The degree of attention modulation at cross-attention layers.
77 | ws : The degree of attention modulation at self-attention layers.
78 | 79 |

80 | 81 |

82 | 83 | ---- 84 | 85 | 86 | ### Benchmark 87 | 88 | We share the benchmark used in our model development and evaluation [here](./dataset). 89 | The code for preprocessing segment conditions is in [here](./inference.ipynb). 90 | 91 | --- 92 | 93 | #### BibTeX 94 | ``` 95 | @inproceedings{densediffusion, 96 | title={Dense Text-to-Image Generation with Attention Modulation}, 97 | author={Kim, Yunji and Lee, Jiyoung and Kim, Jin-Hwa and Ha, Jung-Woo and Zhu, Jun-Yan}, 98 | year={2023}, 99 | booktitle = {ICCV} 100 | } 101 | ``` 102 | 103 | --- 104 | 105 | #### Acknowledgment 106 | The demo was developed referencing this [source code](https://huggingface.co/spaces/weizmannscience/multidiffusion-region-based). Thanks for the inspiring work! 🙏 107 | 108 | -------------------------------------------------------------------------------- /dataset/testset.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/dataset/testset.pkl -------------------------------------------------------------------------------- /dataset/testset_instances.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/dataset/testset_instances.pkl -------------------------------------------------------------------------------- /dataset/testset_layout.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/dataset/testset_layout.tar.gz -------------------------------------------------------------------------------- /dataset/valset.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/dataset/valset.pkl -------------------------------------------------------------------------------- /dataset/valset_layout.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/dataset/valset_layout.tar.gz -------------------------------------------------------------------------------- /eval_iou.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "id": "1731b095", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "# Please refer to the following page for instructions on how to use this evaluation code.\n", 11 | "# https://github.com/naver-ai/DenseDiffusion/issues/16" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": null, 17 | "id": "failing-secret", 18 | "metadata": { 19 | "scrolled": true 20 | }, 21 | "outputs": [], 22 | "source": [ 23 | "import numpy as np\n", 24 | "import os\n", 25 | "import yaml\n", 26 | "import pickle\n", 27 | "from PIL import Image\n", 28 | "\n", 29 | "import torch\n", 30 | "import torch.nn.functional as F\n", 31 | "from torchvision import transforms\n", 32 | "\n", 33 | "from utils.general import non_max_suppression_mask_conf\n", 34 | "\n", 35 | "from detectron2.modeling.poolers import ROIPooler\n", 36 | "from detectron2.structures import Boxes\n", 37 | "from detectron2.utils.memory import retry_if_cuda_oom\n", 38 | "from detectron2.layers import paste_masks_in_image" 39 | ] 40 | }, 41 | { 42 | "cell_type": "code", 43 | "execution_count": null, 44 | "id": "sixth-universe", 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n", 49 | "with open('data/hyp.scratch.mask.yaml') as f:\n", 50 | " hyp = yaml.load(f, Loader=yaml.FullLoader)\n", 51 | "weigths = torch.load('yolov7-mask.pt')\n", 52 | "model = weigths['model']\n", 53 | "model = model.half().eval().to(device)\n", 54 | "\n", 55 | "with open('../dataset/testset_instances.pkl', 'rb') as f:\n", 56 | " inst_gt = pickle.load(f) \n", 57 | " \n", 58 | "trans = transforms.Compose([transforms.Resize(224), \n", 59 | " transforms.CenterCrop(224),\n", 60 | " transforms.ToTensor()])" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "id": "6095e65c", 67 | "metadata": { 68 | "scrolled": true 69 | }, 70 | "outputs": [], 71 | "source": [ 72 | "iou = []\n", 73 | "\n", 74 | "for i in range(len(inst_gt)):\n", 75 | " \n", 76 | " # preprocess\n", 77 | " im_path = os.path.join('../samples/ours/', str(i)+'.png')\n", 78 | " cls_gt = inst_gt[i]['cls_gt']\n", 79 | " mask_gt = inst_gt[i]['mask_gt']\n", 80 | "\n", 81 | " image = trans(Image.open(im_path)).unsqueeze(0)\n", 82 | " image = image.half().to(device)\n", 83 | " \n", 84 | " # predict instance masks and classes\n", 85 | " output = model(image)\n", 86 | " inf_out, attn, bases, sem_output = output['test'], output['attn'], output['bases'], output['sem']\n", 87 | " bases = torch.cat([bases, sem_output], dim=1)\n", 88 | " nb, _, height, width = image.shape\n", 89 | " names = model.names\n", 90 | " pooler_scale = model.pooler_scale\n", 91 | " pooler = ROIPooler(output_size=hyp['mask_resolution'], scales=(pooler_scale,), sampling_ratio=1,\\\n", 92 | " pooler_type='ROIAlignV2', canonical_level=2)\n", 93 | "\n", 94 | " output, output_mask, output_mask_score, _, _ = non_max_suppression_mask_conf(inf_out, attn, bases, pooler, hyp,\n", 95 | " conf_thres=0.5, iou_thres=0.65,\n", 96 | " merge=False, mask_iou=None)\n", 97 | " pred, mask_pred = output[0], output_mask[0]\n", 98 | " base = bases[0]\n", 99 | " if pred == None:\n", 100 | " iou.append(0)\n", 101 | " continue\n", 102 | " \n", 103 | " bboxes = Boxes(pred[:, :4])\n", 104 | " original_mask_pred = mask_pred.view(-1, hyp['mask_resolution'], hyp['mask_resolution'])\n", 105 | " mask_pred = retry_if_cuda_oom(paste_masks_in_image)(original_mask_pred, bboxes, (height, width), threshold=0.5)\n", 106 | " mask_pred = F.interpolate(mask_pred.float().unsqueeze(1),(64,64),\n", 107 | " mode='bicubic',align_corners=False).squeeze(1).detach().cpu().numpy()\n", 108 | " cls_pred = pred[:, 5].detach().cpu().numpy()\n", 109 | " cls_txt_pred = [names[int(p)] for p in cls_pred]\n", 110 | " pred_conf = pred[:, 4].detach().cpu().numpy()\n", 111 | " \n", 112 | " # calculate iou (recall)\n", 113 | " cur_iou = []\n", 114 | " for p in range(len(cls_gt)):\n", 115 | " if cls_gt[p] in cls_txt_pred:\n", 116 | " curidx = cls_txt_pred.index(cls_gt[p])\n", 117 | " intersection = np.logical_and(mask_gt[p], mask_pred[curidx])\n", 118 | " union = np.logical_or(mask_gt[p], mask_pred[curidx])\n", 119 | " cur_iou.append(np.sum(intersection) / np.sum(union))\n", 120 | " del cls_txt_pred[curidx]\n", 121 | " mask_pred = np.concatenate([mask_pred[:curidx,:,:], mask_pred[curidx+1:,:,:]], 0)\n", 122 | " else:\n", 123 | " cur_iou.append(0)\n", 124 | " iou.append(np.mean(cur_iou))\n", 125 | " \n", 126 | "print(np.mean(iou))" 127 | ] 128 | }, 129 | { 130 | "cell_type": "code", 131 | "execution_count": null, 132 | "id": "b527fa06", 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [] 136 | }, 137 | { 138 | "cell_type": "code", 139 | "execution_count": null, 140 | "id": "33260b6a", 141 | "metadata": {}, 142 | "outputs": [], 143 | "source": [] 144 | } 145 | ], 146 | "metadata": { 147 | "kernelspec": { 148 | "display_name": "ldm2", 149 | "language": "python", 150 | "name": "ldm2" 151 | }, 152 | "language_info": { 153 | "codemirror_mode": { 154 | "name": "ipython", 155 | "version": 3 156 | }, 157 | "file_extension": ".py", 158 | "mimetype": "text/x-python", 159 | "name": "python", 160 | "nbconvert_exporter": "python", 161 | "pygments_lexer": "ipython3", 162 | "version": "3.9.15" 163 | } 164 | }, 165 | "nbformat": 4, 166 | "nbformat_minor": 5 167 | } 168 | -------------------------------------------------------------------------------- /figures/example_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/example_0.png -------------------------------------------------------------------------------- /figures/example_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/example_1.png -------------------------------------------------------------------------------- /figures/example_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/example_2.png -------------------------------------------------------------------------------- /figures/method.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/method.png -------------------------------------------------------------------------------- /figures/sample.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/sample.png -------------------------------------------------------------------------------- /figures/step1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step1.png -------------------------------------------------------------------------------- /figures/step2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step2.png -------------------------------------------------------------------------------- /figures/step3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step3.png -------------------------------------------------------------------------------- /figures/step3_.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step3_.png -------------------------------------------------------------------------------- /figures/step4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step4.png -------------------------------------------------------------------------------- /figures/step4_.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/naver-ai/DenseDiffusion/54a2ea645a6211f855212efff1720875cef2c090/figures/step4_.png -------------------------------------------------------------------------------- /gradio_app.py: -------------------------------------------------------------------------------- 1 | import gradio as gr 2 | import numpy as np 3 | import torch 4 | import requests 5 | import random 6 | import os 7 | import sys 8 | import pickle 9 | from PIL import Image 10 | 11 | from tqdm.auto import tqdm 12 | from datetime import datetime 13 | 14 | import diffusers 15 | from diffusers import DDIMScheduler 16 | from transformers import CLIPTextModel, CLIPTokenizer 17 | import torch.nn.functional as F 18 | 19 | from utils import preprocess_mask, process_sketch, process_prompts, process_example 20 | 21 | 22 | ################################################# 23 | ################################################# 24 | ### check diffusers version 25 | if diffusers.__version__ != '0.20.2': 26 | print("Please use diffusers v0.20.2") 27 | sys.exit(0) 28 | 29 | 30 | ################################################# 31 | ################################################# 32 | canvas_html = "
" 33 | load_js = """ 34 | async () => { 35 | const url = "https://huggingface.co/datasets/radames/gradio-components/raw/main/sketch-canvas.js" 36 | fetch(url) 37 | .then(res => res.text()) 38 | .then(text => { 39 | const script = document.createElement('script'); 40 | script.type = "module" 41 | script.src = URL.createObjectURL(new Blob([text], { type: 'application/javascript' })); 42 | document.head.appendChild(script); 43 | }); 44 | } 45 | """ 46 | 47 | get_js_colors = """ 48 | async (canvasData) => { 49 | const canvasEl = document.getElementById("canvas-root"); 50 | return [canvasEl._data] 51 | } 52 | """ 53 | 54 | css = ''' 55 | #color-bg{display:flex;justify-content: center;align-items: center;} 56 | .color-bg-item{width: 100%; height: 32px} 57 | #main_button{width:100%} 58 |