{"id":19832072,"url":"https://github.com/iceclear/ldm-srtuning","last_synced_at":"2025-10-05T18:42:59.790Z","repository":{"id":181558023,"uuid":"666947615","full_name":"IceClear/LDM-SRtuning","owner":"IceClear","description":"Train latent diffusion for real-world super-resolution.","archived":false,"fork":false,"pushed_at":"2023-08-19T07:07:46.000Z","size":2823,"stargazers_count":71,"open_issues_count":6,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-01T16:42:16.389Z","etag":null,"topics":["latent-diffusion","stablesr","super-resolution"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/IceClear.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-16T05:57:45.000Z","updated_at":"2025-04-28T04:38:55.000Z","dependencies_parsed_at":"2024-11-12T11:46:44.107Z","dependency_job_id":null,"html_url":"https://github.com/IceClear/LDM-SRtuning","commit_stats":null,"previous_names":["iceclear/ldm-srtuning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/IceClear/LDM-SRtuning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IceClear%2FLDM-SRtuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IceClear%2FLDM-SRtuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IceClear%2FLDM-SRtuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IceClear%2FLDM-SRtuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IceClear","download_url":"https://codeload.github.com/IceClear/LDM-SRtuning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IceClear%2FLDM-SRtuning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278501865,"owners_count":25997708,"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","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","stablesr","super-resolution"],"created_at":"2024-11-12T11:36:20.403Z","updated_at":"2025-10-05T18:42:59.743Z","avatar_url":"https://github.com/IceClear.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Latent Diffusion Models\nThis repo is used as an example for training and finetuning [latent-diffusion](https://github.com/CompVis/latent-diffusion) used as the baseline in [StableSR](https://github.com/IceClear/StableSR).\n\n## Requirements\nA suitable [conda](https://conda.io/) environment named `ldm` can be created\nand activated with:\n\n```\nconda env create -f environment.yaml\nconda activate ldm\n```\n\n## Pretrained Models\nYou can download our finetuned model [[HuggingFace](https://huggingface.co/Iceclear/StableSR/resolve/main/ldmsr4x_finetune_119.ckpt) | [OpenXLab](https://download.openxlab.org.cn/models/Iceclear/StableSR/weight//ldmsr4x_finetune_119.ckpt)].\n\n## Train\n\n```\npython main.py --base configs/bsr_sr/config_sr_finetune.yaml -t --gpus 0, --train --scale_lr False\n```\n\n## Inference\n\nWe use eta=1.0 as a type of DDPM using the offical DDIM sampling code.\n\n```\npython scripts/sr_val_ddim_realsr.py --config configs/bsr_sr/config_sr_finetune.yaml --ckpt CKPT_PATH --outdir OUTPUT_PATH --skip_grid --ddim_steps 200 --init-img INPUT_PATH --ddim_eta 1.0 --color_fix\n```\n\n## Acknowledgement\n\nThis repo is an extension built on [latent-diffusion](https://github.com/openai/guided-diffusion).\nSome codes are also borrowing from [BasicSR](https://github.com/XPixelGroup/BasicSR).\nThanks for open-sourcing!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ficeclear%2Fldm-srtuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ficeclear%2Fldm-srtuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ficeclear%2Fldm-srtuning/lists"}