{"id":18254627,"url":"https://github.com/haideraqeeb/latent-diffusion","last_synced_at":"2026-01-27T20:08:09.956Z","repository":{"id":256257834,"uuid":"854745054","full_name":"haideraqeeb/latent-diffusion","owner":"haideraqeeb","description":"Text to Image Generator using Latent Diffusion Model","archived":false,"fork":false,"pushed_at":"2025-10-24T15:51:46.000Z","size":859,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-24T17:30:21.479Z","etag":null,"topics":["latent-diffusion","machine-learning","text-to-image"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/haideraqeeb.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,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-09-09T17:50:26.000Z","updated_at":"2025-10-24T15:51:50.000Z","dependencies_parsed_at":"2024-09-16T07:56:23.965Z","dependency_job_id":"983b5a87-0222-460c-99c7-4543a2d4a4a3","html_url":"https://github.com/haideraqeeb/latent-diffusion","commit_stats":null,"previous_names":["haideraqeeb/latent-diffusion"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/haideraqeeb/latent-diffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haideraqeeb%2Flatent-diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haideraqeeb%2Flatent-diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haideraqeeb%2Flatent-diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haideraqeeb%2Flatent-diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/haideraqeeb","download_url":"https://codeload.github.com/haideraqeeb/latent-diffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haideraqeeb%2Flatent-diffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28820352,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-27T18:44:20.126Z","status":"ssl_error","status_checked_at":"2026-01-27T18:44:09.161Z","response_time":168,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["latent-diffusion","machine-learning","text-to-image"],"created_at":"2024-11-05T10:13:06.721Z","updated_at":"2026-01-27T20:08:09.934Z","avatar_url":"https://github.com/haideraqeeb.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# latent-diffusion\n\n## To install dependencies run the command:\n```\npip install -r requirements.txt\n```\n## Download weights and tokenizer files:\n1. Download ```vocab.json``` and ```merges.txt``` from https://www.modelscope.cn/models/AI-ModelScope/stable-diffusion-v1-5/files and save them in the data folder in the root directory.\n2. Download the ```v1-5-pruned-emaonly.ckpt``` and save it in the data folder from the same link.\n\n## To use the model:\n1. Go to the ```script``` folder. Then open the ```demo.ipynb``` notebook.\n2. For text2image task, change the ```prompt``` to the image you want to generate(you can also add ```uncond_prompt``` for the unconditional prompt if you want to exclude something).\n3. For image2image task, first create an ```images``` folder in the root directory, add an image to it, then add the relative path of the image in ```image_path``` variable and finally uncomment the line ```input_image = Image.open(image_path)```.\n4. If you have CUDA support or MPS support then change the ```ALLOW_CUDA``` or ```ALLOW_MPS``` constant to ```True``` for faster processing.\n\n## Sample Generated Images\n##### Prompt: A football stadium, highly detailed, ultra sharp, cinematic, 8k resolution.\n##### Output:\n![stadium](assets/stadium.jpg)\n\n\u003c/br\u003e\n\n##### Prompt: Mosaic art of Taj Mahal using cyberpunk themed art style, 8k resolution.\n##### Output:\n![taj_mahal](assets/taj_mahal.jpg)\n\n\n\n## Special Thanks\nSpecial thanks to the following repositories:\n\n1. https://github.com/CompVis/stable-diffusion/\n2. https://github.com/divamgupta/stable-diffusion-tensorflow\n3. https://github.com/kjsman/stable-diffusion-pytorch\n4. https://github.com/huggingface/diffusers/\n5. https://github.com/hkproj/pytorch-stable-diffusion/tree/main","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaideraqeeb%2Flatent-diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhaideraqeeb%2Flatent-diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaideraqeeb%2Flatent-diffusion/lists"}