-
Hi. I am quite impressed with the performance of the models and methods used in waifu2x and I want to train my own model based on them. It will be a 1x mapping from an image x (RGBA) to an image y (RG…
-
Thank you for making new great feature, Differential Regional Prompter.
I note some issues about it.
1.Hires
I use tutorial prompt about "closed eyes", and it works fine when hires off, but it do…
-
### Your question
Problems with flux dev ggu fp8 q4, please help.
### Logs
```powershell
# ComfyUI Error Report
## Error Details
- **Node Type:** SamplerCustomAdvanced
- **Exception Type:** Runt…
6p5ra updated
3 weeks ago
-
As depicted in the caption the figure you reported (Figure 7) is an ablation study on the Stable Diffusion VAE and EMASC contribution.
The images in the figure are compressed and decompressed using t…
-
hi, thanks for your great, when i'm using your trained models, i have some questions.
1). why the input and output channel in deblock and denoise is 1 ? are those two models only support gray images?…
sjf18 updated
4 years ago
-
Hi,
Thank you for this wonderful work. I m hoping to use this for my project since I do not have the ground truth for the set of ultrasound medical images I am working with. I would really apprecia…
-
Hey, I am trying to train your https://github.com/NVlabs/denoising-diffusion-gan Denoising Diffusion GAN model and my image size is 256. However, the problem is that repository recommends this reposit…
-
I want to use Multi-Task Facial Landmark (MTFL) dataset to train DDPM.
I use the code bellow.
``` python
from denoising_diffusion_pytorch import Unet, GaussianDiffusion, Trainer
model = Unet(
…
-
The inputs for RGB-NIR task are 'noisy_img'(h,w,3), 'guidance_img'(h,w,1) and you split the RGB noisy input images following:
```
with torch.no_grad():
denoised_r, _, _ = model(noisy_im…
-
Hi,
Thanks for your amazing work.
I was wondering where could I download the dataset for the Gaussian image de-noising model.
Referring to the "To evaluate the image denoising performance, w…