{"id":27295826,"url":"https://github.com/adamelliotfields/gradio-diffusion","last_synced_at":"2026-02-16T00:32:30.240Z","repository":{"id":287079070,"uuid":"963263344","full_name":"adamelliotfields/gradio-diffusion","owner":"adamelliotfields","description":"Stable Diffusion inference in Gradio","archived":false,"fork":false,"pushed_at":"2025-04-10T02:07:00.000Z","size":607,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-03T11:54:04.132Z","etag":null,"topics":["controlnet","diffusers","gradio","img2img","ip-adapter","pytorch","stable-diffusion","txt2img"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"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/adamelliotfields.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,"zenodo":null}},"created_at":"2025-04-09T12:12:14.000Z","updated_at":"2025-04-10T02:07:03.000Z","dependencies_parsed_at":"2025-04-09T21:37:20.989Z","dependency_job_id":"85f9301f-78ca-4fc9-87f5-492b871bc18c","html_url":"https://github.com/adamelliotfields/gradio-diffusion","commit_stats":null,"previous_names":["adamelliotfields/gradio-diffusion"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/adamelliotfields/gradio-diffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adamelliotfields%2Fgradio-diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adamelliotfields%2Fgradio-diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adamelliotfields%2Fgradio-diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adamelliotfields%2Fgradio-diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adamelliotfields","download_url":"https://codeload.github.com/adamelliotfields/gradio-diffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adamelliotfields%2Fgradio-diffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29494998,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-16T00:16:34.147Z","status":"ssl_error","status_checked_at":"2026-02-16T00:15:26.759Z","response_time":118,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":["controlnet","diffusers","gradio","img2img","ip-adapter","pytorch","stable-diffusion","txt2img"],"created_at":"2025-04-11T23:29:20.932Z","updated_at":"2026-02-16T00:32:30.224Z","avatar_url":"https://github.com/adamelliotfields.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# gradio-diffusion\n\nGradio app for Stable Diffusion 1.5 featuring:\n* txt2img and img2img pipelines with IP-Adapter\n* ControlNet with Canny edge detection\n* FastNegative textual inversion\n* Real-ESRGAN resizing up to 8x\n* Compel prompt weighting support\n* Multiple samplers with Karras scheduling\n* DeepCache available for faster inference\n\n## Installation\n\n```bash\nuv venv\nuv pip install -r requirements.txt\nuv run app.py\n```\n\n## Usage\n\nEnter a prompt or roll the `🎲` and press `Generate`.\n\n### Prompting\n\nPositive and negative prompts are embedded by [Compel](https://github.com/damian0815/compel). See [syntax features](https://github.com/damian0815/compel/blob/main/doc/syntax.md) to learn more.\n\n### Models\n\nSome require specific parameters to get the best results, so check the model's link for more information:\n\n* [cyberdelia/CyberRealistic_V5](https://huggingface.co/cyberdelia/CyberRealistic)\n* [fluently/Fluently-v4](https://huggingface.co/fluently/Fluently-v4)\n* [Lykon/dreamshaper-8](https://huggingface.co/Lykon/dreamshaper-8)\n* [s6yx/ReV_Animated](https://huggingface.co/s6yx/ReV_Animated)\n* [SG161222/Realistic_Vision_V5](https://huggingface.co/SG161222/Realistic_Vision_V5.1_noVAE)\n* [stable-diffusion-v1-5/stable-diffusion-v1-5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)\n* [XpucT/Deliberate_v6](https://huggingface.co/XpucT/Deliberate)\n* [XpucT/Reliberate_v3](https://huggingface.co/XpucT/Reliberate) (default)\n\n### Scale\n\nRescale up to 8x using [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) with weights from [ai-forever](ai-forever/Real-ESRGAN).\n\n### Image-to-Image\n\nThe `Image-to-Image` settings allows you to provide input images for the initial latent, ControlNet, and IP-Adapter.\n\n#### Strength\n\nInitial image strength (known as _denoising strength_) is essentially how much the generation will differ from the input image. A value of `0` will be identical to the original, while `1` will be a completely new image. You may want to also increase the number of inference steps.\n\nNote that denoising strength only applies to the `Initial Image` input; it doesn't affect ControlNet or IP-Adapter.\n\n#### ControlNet\n\nIn [ControlNet](https://github.com/lllyasviel/ControlNet), the input image is used to get a feature map from an _annotator_. These are computer vision models used for tasks like edge detection and pose estimation. ControlNet models are trained to understand these feature maps. Read the [docs](https://huggingface.co/docs/diffusers/using-diffusers/controlnet) to learn more.\n\nCurrently, the only annotator available is [Canny](https://huggingface.co/lllyasviel/control_v11p_sd15_canny) (edge detection).\n\n#### IP-Adapter\n\nIn an image-to-image pipeline, the input image is used as the initial latent representation. With [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter), the image is processed by a separate image encoder and the encoded features are used as conditioning along with the text prompt.\n\nFor capturing faces, enable `IP-Adapter Face` to use the full-face model. You should use an input image that is mostly a face and it should be high quality.\n\n### Advanced\n\n#### Textual Inversion\n\nAdd `\u003cfast_negative\u003e` anywhere in your negative prompt to apply the [FastNegative v2](https://civitai.com/models/71961?modelVersionId=94057) textual inversion embedding. Read [An Image is Worth One Word](https://huggingface.co/papers/2208.01618) to learn more.\n\n\u003e 💡 Wrap in parens to weight the embedding like `(\u003cfast_negative\u003e)0.8`.\n\n#### DeepCache\n\n[DeepCache](https://github.com/horseee/DeepCache) caches lower UNet layers and reuses them every _n_ steps. Trade quality for speed:\n- *1*: no caching (default)\n- *2*: more quality\n- *3*: balanced\n- *4*: more speed\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamelliotfields%2Fgradio-diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadamelliotfields%2Fgradio-diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamelliotfields%2Fgradio-diffusion/lists"}