add comparsion with GigaGAN's demo
pkuliyi2015
parent
a59a3381f9
commit
4499d79649
|
|
@ -25,15 +25,15 @@ Relevant Links
|
|||
|
||||
- 2023.07.01: We occasionally found that **proper negative prompts can significantly enhance the details of StableSR.**
|
||||
- We use CFG Scale=7 with the following negative prompts: 3d, cartoon, anime, sketches, (worst quality:2), (low quality:2)
|
||||
- Click [comparison](https://imgsli.com/MTg5MjM1) to see the significant power of negative prompts.
|
||||
- In our test, common positive prompts (like masterpiece, best quality, 1girl, realistic) doesn't bring significant improvements.
|
||||
- But we are not sure if there exists some useful positive prompts. Please feel free to share your test results in this repo's discussion panel.
|
||||
- Click [comparison1](https://imgsli.com/MTg5MjM1) to see the significant power of negative prompts.
|
||||
- Postive prompts are not very useful, but it also helps. You can try (masterpiece:2), (best quality:2), (realistic:2),(very clear:2)
|
||||
- With the above prompts, we are trying our best to approach close-source project GigaGAN's quality (while ours are still worse than their demo). Click [comparison2](https://imgsli.com/MTg5MzAx/) to see our current capability on 128x128->1024x1024 upscaling.
|
||||
- 2023.06.30: We are happy to release a new SD 2.1 768 version of StableSR! (Thanks to Jianyi Wang)
|
||||
- It produces similar amount of details, but with **significantly less artifacts** and **better color**.
|
||||
- It supports the resolution of 768 * 768.
|
||||
- To enjoy the new model:
|
||||
- Use the SD 2.1 768 base model. It can be download from [HuggingFace](https://huggingface.co/stabilityai/stable-diffusion-2-1)
|
||||
- The corresponding SR Module (~400MB): [Official Resource](https://huggingface.co/Iceclear/StableSR/blob/main/webui_768v_139.ckpt)
|
||||
- The corresponding SR Module (~400MB): [Official Resource](https://huggingface.co/Iceclear/StableSR/blob/main/webui_768v_139.ckpt), [我的百度网盘-提取码8ju9](https://pan.baidu.com/s/17on7GA2RLvVzdDnBwA0N0g?pwd=8ju9)
|
||||
- Now you can use a larger tile size in the Tiled Diffusion (96 * 96, the same as default settings), the speed can be slightly faster.
|
||||
- Keep other things the same.
|
||||
- Janyi Wang keeps trying to train more powerful SR modules suitable for AIGC images. These models will be tuned on SD2.1 768 or SDXL later.
|
||||
|
|
|
|||
|
|
@ -22,17 +22,17 @@ Licensed under S-Lab License 1.0
|
|||
|
||||
## 重要更新
|
||||
|
||||
- 2023.07.01: 我们偶然发现 **合适的负面prompt会大幅提高StableSR的生成质量.**
|
||||
- 2023.07.01: 我们偶然发现 **合适的负面提示词会大幅提高StableSR的生成质量.**
|
||||
- 我们使用了CFG Scale=7以及下面的负面提示词：3d, cartoon, anime, sketches, (worst quality:2), (low quality:2)
|
||||
- 点击[对比](https://imgsli.com/MTg5MjM1)来查看负面提示词的威力
|
||||
- 在我们的测试中, 常见正面提示词（比如masterpiece, best quality, 1girl, realistic）没有什么显著效果。
|
||||
- 但我们不确定到底有没有有用的正面提示词。欢迎在本仓库的讨论区中分享你的测试结果.
|
||||
- 正面提示词用处不大，但你依然可以尝试下面的提示词：(masterpiece:2), (best quality:2), (realistic:2),(very clear:2)
|
||||
- 使用上面提示词，我们正努力接近闭源方法GigaGAN的放大效果（虽然还有差距）。点击[comparison2](https://imgsli.com/MTg5MzAx/)看看实力。
|
||||
- 2023.06.30: 我们很高兴发布 StableSR 的新版本 SD 2.1 768！（感谢 Jianyi Wang）
|
||||
- 它产生类似的细节，但具有**更自然的边缘（更少的白边黑边）**和**更好的颜色**。
|
||||
- 它支持 768 * 768 的分辨率。
|
||||
- 要使用新模型：
|
||||
- 使用 SD 2.1 768 基础模型。可以从[HuggingFace](https://huggingface.co/stabilityai/stable-diffusion-2-1)下载。
|
||||
- 下载相应的 SR 模块（约400MB）：[官方资源](https://huggingface.co/Iceclear/StableSR/blob/main/webui_768v_139.ckpt)
|
||||
- 下载相应的 SR 模块（约400MB）：[官方资源](https://huggingface.co/Iceclear/StableSR/blob/main/webui_768v_139.ckpt)，[我的百度网盘-提取码8ju9](https://pan.baidu.com/s/17on7GA2RLvVzdDnBwA0N0g?pwd=8ju9)
|
||||
- 现在在 Tiled Diffusion 中可以使用更大的块大小（96 * 96，与默认设置相同），速度可能会稍微更快。
|
||||
- 其他设置保持不变。
|
||||
- Jianyi Wang一直在努力训练更强大的适用于 AIGC 图像的 SR 模块。这些模型都将基于 SD2.1 768 或 SDXL 进行调整。SD2.1 512版本将不再继续尝试。
|
||||
|
|
|
|||
Loading…
Reference in New Issue