{"id":19220935,"url":"https://github.com/keturn/sd-progress-demo","last_synced_at":"2025-05-13T01:14:53.911Z","repository":{"id":59920369,"uuid":"538190964","full_name":"keturn/sd-progress-demo","owner":"keturn","description":"cheap views of intermediate Stable Diffusion results","archived":false,"fork":false,"pushed_at":"2022-09-22T16:22:02.000Z","size":57,"stargazers_count":45,"open_issues_count":0,"forks_count":4,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-05-13T01:14:43.574Z","etag":null,"topics":["diffusers","gradio","jupyter-notebook","stable-diffusion","stable-diffusion-diffusers"],"latest_commit_sha":null,"homepage":"https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/2?u=keturn","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/keturn.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}},"created_at":"2022-09-18T17:45:09.000Z","updated_at":"2024-10-11T04:43:28.000Z","dependencies_parsed_at":"2022-09-25T07:34:06.268Z","dependency_job_id":null,"html_url":"https://github.com/keturn/sd-progress-demo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keturn%2Fsd-progress-demo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keturn%2Fsd-progress-demo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keturn%2Fsd-progress-demo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keturn%2Fsd-progress-demo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keturn","download_url":"https://codeload.github.com/keturn/sd-progress-demo/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253851074,"owners_count":21973674,"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":["diffusers","gradio","jupyter-notebook","stable-diffusion","stable-diffusion-diffusers"],"created_at":"2024-11-09T14:37:50.689Z","updated_at":"2025-05-13T01:14:53.853Z","avatar_url":"https://github.com/keturn.png","language":"Python","readme":"---\ntitle: Diffusers Preview Demo\nemoji: 📉\ncolorFrom: blue\ncolorTo: blue\nsdk: gradio\nsdk_version: 3.3.1\napp_file: app.py\npinned: false\n---\n\nHere we demonstrate how to do preview images of a Stable Diffusion's intermediate stages using a [fast approximation][approximation] to visualize the low-resolution (64px) latent state.\n\n+ **[app.py](app.py)** is a Gradio application that yields preview images from a [generator function][gradio.iter] while the pipeline is in progress. The UI is directly derived from Stability AI's [Stable Diffusion Demo](https://huggingface.co/spaces/stabilityai/stable-diffusion).\n+ **[progress_ipywidgets_demo.ipynb](progress_ipywidgets_demo.ipynb)** demonstrates using the same pipeline to update [Jupyter widgets][ipywidgets] in a notebook.\n+ [`preview_decoder.py`](preview_decoder.py) has the fast latent-to-RGB decoder function.\n+ [`generator_pipeline.py`](generator_pipeline.py) provides a DiffusionPipeline with a `generate()` method to yield the latent data at each step. It is nearly a strict refactoring of the [StableDiffusionPipeline][sdpipeline] in 🧨diffusers 0.3.\n\n[approximation]: https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/2?u=keturn \"Decoding latents to RGB without upscaling\"\n[ipywidgets]: https://ipywidgets.readthedocs.io/en/stable/\n[gradio.iter]: https://gradio.app/key_features/#iterative-outputs\n[sdpipeline]: https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fketurn%2Fsd-progress-demo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fketurn%2Fsd-progress-demo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fketurn%2Fsd-progress-demo/lists"}