nodes/ali-vilab-ACE_plus
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

modify readme

Browse Source
This commit is contained in:
皓童
2025-01-07 14:36:57 +08:00
parent 87b62fcfdc
commit 627bbbae9c
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -6
View File
@@ -43,12 +43,12 @@
## 🔥 ACE Models
ACE++ provides a comprehensive toolkit for image editing and generation to support various applications. We encourage developers to choose the appropriate model based on their own scenarios and to fine-tune their models using data from their specific scenarios to achieve more stable results.
| **Model** | *Tuning Method* | **Description** | **Examples** | **Model Path(scepter_path)** |
|:------------------:|:------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| ACE++ Portrait | LoRA + ACE Data | Portrait-consistent generation to <br> maintain the consistency of the portrait . | <img src="./assets/samples/portrait/human_1.jpg" alt="Image 1" height="256" style="display:inline-block;"/> <img src="./assets/samples/portrait/human_1_1.jpg" alt="Image 2" height="256" style="display:inline-block;"/><br><p style="display:inline-block;">Maintain the facial features, A girl is wearing a neat police uniform and sporting a badge. <br> She is smiling with a friendly and confident demeanor. The background is blurred, featuring a cartoon logo. </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@portrait/comfyui_portrait_lora64.safetensors] <br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/portrait/) <br> hf://ali-vilab/ACE_Plus@portrait/comfyui_portrait_lora64.safetensors |
| ACE++ Subject | LoRA + ACE Data | Subject-driven image generation <br> task to maintain the consistency of <br> a specific subject in different scenes. | <img src="./assets/samples/subject/subject_1.jpg" alt="Image 1" height="256" style="display:inline-block;"/> <img src="./assets/samples/subject/subject_1_1.jpg" alt="Image 2" height="256" style="display:inline-block;"/><br><p style="display:inline-block;">Display the logo in a minimalist style printed in white on a matte black ceramic coffee mug, alongside a steaming cup of coffee on a cozy cafe table. </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@subject/comfyui_subject_lora16.safetensors]<br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/subject/) <br> hf://ali-vilab/ACE_Plus@subject/comfyui_subject_lora16.safetensors |
| ACE++ LocalEditing | LoRA + ACE Data | Redrawing the mask area of images <br> while maintaining the original structural <br> information of the edited area. | <img src="./assets/samples/local/local_1.webp" alt="Image 1" height="160" style="display:inline-block;"/> <img src="./assets/samples/local/local_1_m.webp" alt="Image 1" height="160" style="display:inline-block;"/> <img src="./assets/samples/local/local_1_1.jpg" alt="Image 2" height="160" style="display:inline-block;"/><br><p style="display:inline-block;">By referencing the mask, restore a partial image from the doodle {image} that aligns with the textual explanation: "1 white old owl". </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@local_editing/comfyui_local_lora16.safetensors] <br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/local_editing/) <br> hf://ali-vilab/ACE_Plus@local_editing/comfyui_local_lora16.safetensors |
| ACE++ | Full Finetune + ACE Data |Fully finetuning a composite model with ACE’s <br> data to support various editing and reference <br> generation tasks through an instructive approach. | | Will be released soon. |
| **Model** | *Tuning Method* | **Description** | **Examples** | **Model Path(scepter_path)** |
|:------------------:|:------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| ACE++ Portrait | LoRA + ACE Data | Portrait-consistent generation to <br> maintain the consistency of the portrait . | <img src="./assets/samples/portrait/human_1.jpg" alt="Image 1" height="256" style="display:inline-block;"/> <img src="./assets/samples/portrait/human_1_1.jpg" alt="Image 2" height="256" style="display:inline-block;"/><br><p style="display:inline-block;">Maintain the facial features, A girl is wearing a neat police uniform and sporting a badge. <br> She is smiling with a friendly and confident demeanor. The background is blurred, featuring a cartoon logo. </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@portrait/xxxx.safetensors] <br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/portrait/) <br> hf://ali-vilab/ACE_Plus@portrait/xxxx.safetensors |
| ACE++ Subject | LoRA + ACE Data | Subject-driven image generation <br> task to maintain the consistency of <br> a specific subject in different scenes. | <img src="./assets/samples/subject/subject_1.jpg" alt="Image 1" height="256" style="display:inline-block;"/> <img src="./assets/samples/subject/subject_1_1.jpg" alt="Image 2" height="256" style="display:inline-block;"/><br><p style="display:inline-block;">Display the logo in a minimalist style printed in white on a matte black ceramic coffee mug, alongside a steaming cup of coffee on a cozy cafe table. </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@subject/xxxx.safetensors]<br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/subject/) <br> hf://ali-vilab/ACE_Plus@subject/xxxx.safetensors |
| ACE++ LocalEditing | LoRA + ACE Data | Redrawing the mask area of images <br> while maintaining the original structural <br> information of the edited area. | <img src="./assets/samples/local/local_1.webp" alt="Image 1" height="160" style="display:inline-block;"/> <img src="./assets/samples/local/local_1_m.webp" alt="Image 1" height="160" style="display:inline-block;"/> <img src="./assets/samples/local/local_1_1.jpg" alt="Image 2" height="160" style="display:inline-block;"/><br><p style="display:inline-block;">By referencing the mask, restore a partial image from the doodle {image} that aligns with the textual explanation: "1 white old owl". </p> | [![ModelScope link](https://img.shields.io/badge/ModelScope-Model-blue)](https://www.modelscope.cn/models/iic/ACE_Plus/) <br> ms://iic/ACE_Plus@local_editing/xxxx.safetensors] <br> [![HuggingFace link](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow)](https://huggingface.co/ali-vilab/ACE_Plus/tree/main/local_editing/) <br> hf://ali-vilab/ACE_Plus@local_editing/xxxx.safetensors |
| ACE++ | Full Finetune + ACE Data |Fully finetuning a composite model with ACE’s <br> data to support various editing and reference <br> generation tasks through an instructive approach. | | Will be released soon. |
## 🔥 Applications
The ACE++ model supports a wide range of downstream tasks through simple adaptations. Here are some examples, and we look forward to seeing the community explore even more exciting applications utilizing the ACE++ model.