Update README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,9 @@ Please refer to [S-Lab License 1.0](https://github.com/IceClear/StableSR/blob/ma
|
|
27 |
|
28 |
### Limitations
|
29 |
|
30 |
-
-
|
|
|
|
|
31 |
|
32 |
### Bias
|
33 |
While our model is based on a pre-trained Stable Diffusion model, currently we do not observe obvious bias in generated results.
|
@@ -55,8 +57,9 @@ StableSR is an image super-resolution model finetuned on [Stable Diffusion](http
|
|
55 |
|
56 |
We currently provide the following checkpoints:
|
57 |
|
58 |
-
- [stablesr_000117.ckpt](https://huggingface.co/Iceclear/StableSR/resolve/main/stablesr_000117.ckpt): Diffusion model finetuned on DF2K_OST dataset for 117 epochs.
|
59 |
- [vqgan_cfw_00011.ckpt](https://huggingface.co/Iceclear/StableSR/resolve/main/vqgan_cfw_00011.ckpt): CFW module with fixed VQGAN trained on synthetic paired data for 11 epochs.
|
|
|
60 |
|
61 |
## Evaluation Results
|
62 |
See [Paper](https://arxiv.org/abs/2305.07015) for details.
|
|
|
27 |
|
28 |
### Limitations
|
29 |
|
30 |
+
- StableSR still requires multiple steps for generating a large image beyond 512 or 768, which is much slower than GAN-based approaches.
|
31 |
+
- StableSR sometimes cannot keep 100% fidelity due to its generative nature.
|
32 |
+
- StableSR sometimes cannot generate perfect details under complex real-world scenarios.
|
33 |
|
34 |
### Bias
|
35 |
While our model is based on a pre-trained Stable Diffusion model, currently we do not observe obvious bias in generated results.
|
|
|
57 |
|
58 |
We currently provide the following checkpoints:
|
59 |
|
60 |
+
- [stablesr_000117.ckpt](https://huggingface.co/Iceclear/StableSR/resolve/main/stablesr_000117.ckpt): Diffusion model finetuned on [SD2.1-512base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base) with DF2K_OST dataset for 117 epochs.
|
61 |
- [vqgan_cfw_00011.ckpt](https://huggingface.co/Iceclear/StableSR/resolve/main/vqgan_cfw_00011.ckpt): CFW module with fixed VQGAN trained on synthetic paired data for 11 epochs.
|
62 |
+
- [stablesr_768v_000139.ckpt](https://huggingface.co/Iceclear/StableSR/blob/main/stablesr_768v_000139.ckpt): Diffusion model finetuned on [SD2.1-768v](https://huggingface.co/stabilityai/stable-diffusion-2-1) with DF2K_OST dataset for 139 epochs.
|
63 |
|
64 |
## Evaluation Results
|
65 |
See [Paper](https://arxiv.org/abs/2305.07015) for details.
|