diff --git a/asset/images/edit_tuner/clay_cat.jpeg b/asset/images/edit_tuner/clay_cat.jpeg new file mode 100644 index 0000000..c8fb430 Binary files /dev/null and b/asset/images/edit_tuner/clay_cat.jpeg differ diff --git a/asset/images/edit_tuner/clay_vermeer.jpeg b/asset/images/edit_tuner/clay_vermeer.jpeg new file mode 100644 index 0000000..757c072 Binary files /dev/null and b/asset/images/edit_tuner/clay_vermeer.jpeg differ diff --git a/asset/images/edit_tuner/vermeer.jpeg b/asset/images/edit_tuner/vermeer.jpeg new file mode 100644 index 0000000..7d6fb9e Binary files /dev/null and b/asset/images/edit_tuner/vermeer.jpeg differ diff --git a/readme.md b/readme.md index 7c59a14..9e9aa0e 100644 --- a/readme.md +++ b/readme.md @@ -18,7 +18,7 @@ SCEPTER offers 3 core components: ## 🎉 News -- [2024.05]: Introducing SCEPTER v1, supporting customized image edit tasks! Simply provide 10 image pairs, SCEPTER will tune an edit tuner for your own Image-to-Image tasks, like `de-text`, `segmentation`, etc. +- [2024.05]: Introducing SCEPTER v1, supporting customized image edit tasks! Simply provide 10 image pairs, SCEPTER will tune an edit tuner for your own Image-to-Image tasks, like `Clay Style`, `De-Text`, `Segmentation`, etc. - [2024.04]: New [StyleBooth](https://ali-vilab.github.io/stylebooth-page/) demo on SCEPTER Studio for`Text-Based Style Editing`. - [2024.03]: We optimize the training UI and checkpoint management. New [LAR-Gen](https://arxiv.org/abs/2403.19534) model has been added on SCEPTER Studio, supporting `zoom-out`, `virtual try on`, `inpainting`. - [2024.02]: We release new SCEdit controllable image synthesis models for SD v2.1 and SD XL. Multiple strategies applied to accelerate inference time for SCEPTER Studio. @@ -32,11 +32,20 @@ SCEPTER offers 3 core components: ### Edit Tuners -Simply provide 10 image pairs, SCEPTER will tune an edit tuner for your own Image-to-Image tasks, like `de-text`, `segmentation`, etc. -Try our official few-shot datasets: [De-Text](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdetext.zip), [Image2Hed](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fhed_pair.zip), [image2depth](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fimage2depth.zip), [depth2image](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdepth2image.zip). +Simply provide 10 image pairs, SCEPTER will tune an edit tuner for your own Image-to-Image tasks, like `Clay Style`, `De-Text`, `Segmentation`, etc. +Try our official few-shot datasets: [De-Text](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdetext.zip), [Image2Hed](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fhed_pair.zip), [Image2Depth](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fimage2depth.zip), [Depth2Image](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdepth2image.zip). + + + + + + + + + diff --git a/scepter/methods/studio/extensions/tuners/official_tuners.yaml b/scepter/methods/studio/extensions/tuners/official_tuners.yaml index 868c32c..3016bce 100644 --- a/scepter/methods/studio/extensions/tuners/official_tuners.yaml +++ b/scepter/methods/studio/extensions/tuners/official_tuners.yaml @@ -1,4 +1,13 @@ TUNERS: + - NAME: Clay-Style-Editing + NAME_ZH: 黏土风 + SOURCE: scepter + DESCRIPTION: None + BASE_MODEL: EDIT + MODEL_PATH: ms://iic/stylebooth@tuners/clay_style_edit/ + IMAGE_PATH: ms://iic/stylebooth@tuners/clay_style_edit/image.jpg + TUNER_TYPE: LORA + PROMPT_EXAMPLE: Convert this image into clay style - NAME: Azure-Dragon NAME_ZH: 青龙 SOURCE: scepter
Clay Style
Prompt: "Convert this image into clay style"
De-Text
Prompt: "Remove the texts"		 Image2Hed
Prompt: "Convert to an edge map"