🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru
Colab | Info |
---|---|
DemoFusion_colab | |
DemoFusion_img2img_colab (Thanks to radamar ❤) |
Kaggle | Info |
---|---|
DemoFusion_kaggle | |
DemoFusion_img2img_kaggle |
2048x2048 will take around 800 seconds. (T4)
view_batch_size
(int, defaults to 16): The batch size for multiple denoising paths. Typically, a larger batch size can result in higher efficiency but comes with increased GPU memory requirements.
stride
(int, defaults to 64): The stride of moving local patches. A smaller stride is better for alleviating seam issues, but it also introduces additional computational overhead and inference time.
cosine_scale_1
(float, defaults to 3): Control the strength of skip-residual. For specific impacts, please refer to Appendix C in the DemoFusion paper.
cosine_scale_2
(float, defaults to 1): Control the strength of dilated sampling. For specific impacts, please refer to Appendix C in the DemoFusion paper.
cosine_scale_3
(float, defaults to 1): Control the strength of the Gaussian filter. For specific impacts, please refer to Appendix C in the DemoFusion paper.
sigma
(float, defaults to 1): The standard value of the Gaussian filter. Larger sigma promotes the global guidance of dilated sampling, but has the potential of over-smoothing.
multi_decoder
(bool, defaults to True): Determine whether to use a tiled decoder. Generally, when the resolution exceeds 3072x3072, a tiled decoder becomes necessary.
show_image
(bool, defaults to False): Determine whether to show intermediate results during generation.
https://github.com/PRIS-CV/DemoFusion
https://arxiv.org/abs/2311.16973
https://ruoyidu.github.io/demofusion/demofusion.html
2023-12-07.08-44-13.mp4
guigjk.mp4
DemoFusion_img2img_colab