{"id":13488665,"url":"https://sungnyun.github.io/diffblender/","last_synced_at":"2025-03-28T01:37:05.402Z","repository":{"id":169756019,"uuid":"644758675","full_name":"sungnyun/diffblender","owner":"sungnyun","description":"DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models","archived":false,"fork":false,"pushed_at":"2023-12-21T13:26:55.000Z","size":9761,"stargazers_count":46,"open_issues_count":2,"forks_count":0,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-03-25T22:21:33.547Z","etag":null,"topics":["diffusion","generative-model","multimodal","text-to-image"],"latest_commit_sha":null,"homepage":"https://sungnyun.github.io/diffblender","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sungnyun.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-05-24T07:42:08.000Z","updated_at":"2025-03-06T12:15:29.000Z","dependencies_parsed_at":"2023-12-21T15:54:18.997Z","dependency_job_id":null,"html_url":"https://github.com/sungnyun/diffblender","commit_stats":null,"previous_names":["sungnyun/diffblender"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sungnyun%2Fdiffblender","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sungnyun%2Fdiffblender/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sungnyun%2Fdiffblender/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sungnyun%2Fdiffblender/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sungnyun","download_url":"https://codeload.github.com/sungnyun/diffblender/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245952894,"owners_count":20699555,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["diffusion","generative-model","multimodal","text-to-image"],"created_at":"2024-07-31T18:01:19.745Z","updated_at":"2025-03-28T01:37:05.395Z","avatar_url":"https://github.com/sungnyun.png","language":"Python","funding_links":[],"categories":["Additional conditions"],"sub_categories":[],"readme":"# DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models 🔥\n\n\u003ca href='https://sungnyun.github.io/diffblender/'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-yellow'\u003e\u003c/a\u003e\n\u003ca href='https://arxiv.org/abs/2305.15194'\u003e\u003cimg src='https://img.shields.io/badge/Paper-Arxiv-red'\u003e\u003c/a\u003e  \u003ca href=#bibtex\u003e\u003cimg src='https://img.shields.io/badge/Paper-BibTex-Green'\u003e\u003c/a\u003e \n\u003ca href='https://huggingface.co/sungnyun/diffblender'\u003e\u003cimg src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DiffBlender_Model-blue'\u003e\u003c/a\u003e\n\n\n- **DiffBlender** successfully synthesizes complex combinations of input modalities. It enables flexible manipulation of conditions, providing the customized generation aligned with user preferences. \n- We designed its structure to intuitively extend to additional modalities while achieving a low training cost through a partial update of hypernetworks. \n\n\u003cp align=\"center\"\u003e\n\u003cimg width=\"1369\" alt=\"teaser\" src=\"./assets/fig1.png\"\u003e\n\u003c/p\u003e\n\n## 🗓️ TODOs\n\n- [x] Project page is open: [link](https://sungnyun.github.io/diffblender/)\n- [x] DiffBlender model: code \u0026 checkpoint\n- [x] Release inference code\n- [ ] Release training code \u0026 pipeline\n- [ ] Gradio UI\n\n## 🚀 Getting Started\nInstall the necessary packages with:\n```sh\n$ pip install -r requirements.txt\n```\n\nDownload DiffBlender model checkpoint from this [Huggingface model](https://huggingface.co/sungnyun/diffblender), and place it under `./diffblender_checkpoints/`.    \nAlso, prepare the SD model from this [link](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) (we used CompVis/sd-v1-4.ckpt).\n\n## ⚡️ Try Multimodal T2I Generation with DiffBlender\n```sh\n$ python inference.py --ckpt_path=./diffblender_checkpoints/{CKPT_NAME}.pth \\\n                      --official_ckpt_path=/path/to/sd-v1-4.ckpt \\\n                      --save_name={SAVE_NAME} \n```\n\nResults will be saved under `./inference/{SAVE_NAME}/`, in the format as {conditions + generated image}.\n\n\n \n## BibTeX\n```\n@article{kim2023diffblender,\n  title={DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models},\n  author={Kim, Sungnyun and Lee, Junsoo and Hong, Kibeom and Kim, Daesik and Ahn, Namhyuk},\n  journal={arXiv preprint arXiv:2305.15194},\n  year={2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/sungnyun.github.io%2Fdiffblender%2F","html_url":"https://awesome.ecosyste.ms/projects/sungnyun.github.io%2Fdiffblender%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/sungnyun.github.io%2Fdiffblender%2F/lists"}