{"id":13488339,"url":"https://github.com/Zeqiang-Lai/Mini-DALLE3","last_synced_at":"2025-03-28T00:33:40.906Z","repository":{"id":199076258,"uuid":"694713098","full_name":"Zeqiang-Lai/Mini-DALLE3","owner":"Zeqiang-Lai","description":"Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models ","archived":false,"fork":false,"pushed_at":"2023-12-28T13:53:32.000Z","size":172,"stargazers_count":307,"open_issues_count":7,"forks_count":29,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-24T09:05:41.285Z","etag":null,"topics":["dall-e-3","dalle","dalle-3","dalle3","interactive-text-to-image","mini-dalle3"],"latest_commit_sha":null,"homepage":"https://minidalle3.github.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Zeqiang-Lai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-09-21T14:41:39.000Z","updated_at":"2025-02-27T08:51:26.000Z","dependencies_parsed_at":"2024-01-16T09:02:50.924Z","dependency_job_id":"8a074964-ffce-4626-a6a7-869a80bbe5ff","html_url":"https://github.com/Zeqiang-Lai/Mini-DALLE3","commit_stats":null,"previous_names":["zeqiang-lai/mini-dalle3"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Zeqiang-Lai%2FMini-DALLE3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Zeqiang-Lai%2FMini-DALLE3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Zeqiang-Lai%2FMini-DALLE3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Zeqiang-Lai%2FMini-DALLE3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Zeqiang-Lai","download_url":"https://codeload.github.com/Zeqiang-Lai/Mini-DALLE3/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245949275,"owners_count":20698912,"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":["dall-e-3","dalle","dalle-3","dalle3","interactive-text-to-image","mini-dalle3"],"created_at":"2024-07-31T18:01:14.033Z","updated_at":"2025-03-28T00:33:35.865Z","avatar_url":"https://github.com/Zeqiang-Lai.png","language":"Python","funding_links":[],"categories":["T2I Diffusion Model augmentation"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003ca href=\"https://minidalle3.github.io/\"\u003e\n    \u003cimg src=\"https://github.com/Zeqiang-Lai/Mini-DALLE3/assets/26198430/9594f306-cc1a-4a92-bca2-0c64e8daf9c9\" alt=\"minidalle3\" width=\"19%\"\u003e\n    \u003c/a\u003e \u0026ensp; \n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"http://arxiv.org/abs/2310.07653\"\u003eTechnical Report\u003c/a\u003e •\n\u003ca href=\"https://minidalle3.github.io/\"\u003eProject page\u003c/a\u003e •\n\u003ca href=\"#\"\u003eDemo (Temporarily Unavailable)\u003c/a\u003e\n\u003c/p\u003e\n\n\nhttps://github.com/Zeqiang-Lai/Mini-DALLE3/assets/26198430/5b6c0a0c-ebbf-48db-981e-f97d542a38b4\n\n\n\n![teaser4](https://github.com/Zeqiang-Lai/Mini-DALLE3/assets/26198430/1f17e3c3-6804-4c4e-9266-e902ecedeae8)\n\n\n\u003e An experimental attempt to obtain the interactive and interleave text-to-image and text-to-text experience of [DALL•E 3](https://openai.com/dall-e-3) and [ChatGPT](https://openai.com/chatgpt).\n\n## Try Yourself 🤗 \n\n- Download the [checkpoint](https://huggingface.co/h94/IP-Adapter) and save it as following \n```bash\ncheckpoints\n   - models\n   - sdxl_models\n```\n\n- run the following commands, and you will get a gradio-based web demo.\n\n```bash\nexport OPENAI_API_KEY=\"your key\"\npython -m minidalle3.web \n```\n\n- To use other LLM rather than ChatGPT, such as `baichuan`.\n\n```bash\npython -m minidalle3.llm.baichuan\nexport OPENAI_API_BASE=\"http://0.0.0.0:10039/v1\"\npython -m minidalle3.web\n```\n\n\u003e  `chatglm`, `baichuan`, `internlm` are tested.\n\u003e llama have not supported yet. qwen is not tested.\n\n## TODO\n\n- [x] Support generating image interleaved in the conversations.\n- [ ] Support generating multiple images at once.\n- [ ] Support selecting image.\n- [ ] Support refinement.\n- [ ] Support prompt refinement/variation.\n- [ ] Instruct tuned LLM/SD.\n\n\n## Citation\n\nIf you find this repo helpful, please consider citing us.\n\n```bibtex\n@misc{minidalle3,\n    author={Lai, Zeqiang and Zhu, Xizhou and Dai, Jifeng and Qiao, Yu and Wang, Wenhai},\n    title={Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models},\n    year={2023},\n    url={https://github.com/Zeqiang-Lai/Mini-DALLE3},\n}\n```\n\n## Acknowledgement\n\n[IP-Adapter](https://github.com/tencent-ailab/IP-Adapter) • [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)\n\n![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2FZeqiang-Lai%2FMini-DALLE3\u0026countColor=%23263759\u0026style=flat)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZeqiang-Lai%2FMini-DALLE3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FZeqiang-Lai%2FMini-DALLE3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZeqiang-Lai%2FMini-DALLE3/lists"}