From 1180f450ca382f53a8da6a98810ad74ca5237e60 Mon Sep 17 00:00:00 2001 From: Qianyi Zhao <49068354+Qing112@users.noreply.github.com> Date: Tue, 5 Nov 2024 03:45:33 -0600 Subject: [PATCH] Update introduction.md --- docs/source/introduction/introduction.md | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/docs/source/introduction/introduction.md b/docs/source/introduction/introduction.md index b190246..d9c75a4 100644 --- a/docs/source/introduction/introduction.md +++ b/docs/source/introduction/introduction.md @@ -6,9 +6,11 @@ 目前的开源 Diffusion 模型结构五花八门，以文生图模型为例，有 Stable Diffusion、Kolors、FLUX 等。 -|FLUX|Stable Diffusion 3|Kolors|Hunyuan-DiT|Stable Diffusion|Stable Diffusion XL| +| FLUX | Stable Diffusion 3 | Kolors | Hunyuan-DiT | Stable Diffusion | Stable Diffusion XL | |-|-|-|-|-|-| -|![image_1024_cfg](https://github.com/user-attachments/assets/984561e9-553d-4952-9443-79ce144f379f)|![image_1024](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/4df346db-6f91-420a-b4c1-26e205376098)|![image_1024](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/53ef6f41-da11-4701-8665-9f64392607bf)|![image_1024](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/60b022c8-df3f-4541-95ab-bf39f2fa8bb5)|![1024](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/6fc84611-8da6-4a1f-8fee-9a34eba3b4a5)|![1024](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/67687748-e738-438c-aee5-96096f09ac90)| +| | | | | | | + + 我们设计了统一的框架，实现了通用的增强模块，例如提示词分区控制技术。 @@ -26,13 +28,21 @@ |Without LoRA|![image_without_lora](https://github.com/user-attachments/assets/df62cef6-d54f-4e3d-a602-5dd290079d49)|![image_without_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/9d79ed7a-e8cf-4d98-800a-f182809db318)|![image_without_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/ddb834a5-6366-412b-93dc-6d957230d66e)|![image_without_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/1aa21de5-a992-4b66-b14f-caa44e08876e)| |With LoRA|![image_with_lora](https://github.com/user-attachments/assets/4fd39890-0291-4d19-8a88-d70d0ae18533)|![image_with_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/02f62323-6ee5-4788-97a1-549732dbe4f0)|![image_with_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/8e7b2888-d874-4da4-a75b-11b6b214b9bf)|![image_with_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/83a0a41a-691f-4610-8e7b-d8e17c50a282)| + +||FLUX.1-dev|Kolors|Stable Diffusion 3|Hunyuan-DiT| +|-|-|-|-|-| +|Without LoRA|image_without_lora|image_without_lora|image_without_lora|image_without_lora| +|With LoRA|image_with_lora|image_with_lora|image_with_lora|image_with_lora| + + ## 互联 与语言模型不同，Diffusion 模型存在生态模型，包括 LoRA、ControlNet、IP-Adapter 等，这些模型由不同的开发者开发、训练、开源，我们为这些模型提供了一站式的推理支持。例如基于 Stable Diffusion XL，你可以随意使用这些相关的生态模型组装出丰富的功能。 |底模生成|使用 ControlNet 保持画面结构重新生成|继续叠加 LoRA 使画面更扁平|叠加 IP-Adapter 转换为水墨风格| |-|-|-|-| -|![image](https://github.com/user-attachments/assets/cc094e8f-ff6a-4f9e-ba05-7a5c2e0e609f)|![image_controlnet](https://github.com/user-attachments/assets/d50d173e-e81a-4d7e-93e3-b2787d69953e)|![image_lora](https://github.com/user-attachments/assets/c599b2f8-8351-4be5-a6ae-8380889cb9d8)|![image_ipadapter](https://github.com/user-attachments/assets/e5924aef-03b0-4462-811f-a60e2523fd7f)| +||||| + 你甚至可以继续叠加 AnimateDiff 构建视频转绘方案。