-
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(
…
-
Is there a way to scale existing image (not generated)?
-
Even moderately sized images (I tested 1500x2500 png) had almost no denoising at `-n 3`.
Might be good to add an option for small, medium and large images as well as multi-pass.
Small images it…
-
When i use soft inpainting with a high mask blur value like 40, the example below i just asked for a generic 1girl for testing purposes, on inpainting the prompt was peace sign, the preview result is …
-
I see some dynamic between the 2 but Im not clear on how one affects the other. The steps I define vary in execution and I see a relationship with --init-image-strength. Insights welcome.
-
### Describe the bug
I'm working on implementing scheduled prompting in SDNext and realized that the callback in SDXL pipelines is fundamentally not functional. This also applies to Stable Diffusion …
-
Hi,
I have read your paper titled Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss and I have one question regarding the region-aware cycle loss.
In m…
-
The CryoET Workflow article is live on the docs site, but there are a few improvements needed.
- [ ] For all figures use 75% fill and trim whitespace for any graphics that have large borders
- [ ] F…
-
GPU: NVIDIA H20
音频长度: 1分30秒
音频格式: wav
图片格式: png
图片大小: 208K, 525x526, 25 fps, 25 tbr, 25 tbn
分支: main
配置:
## configs/prompts/animation_acc.yaml
## dependency models
pretrained_base_mod…
-
### Describe the bug
SD3 inpaint pipeline can not use EulerA scheduler.
### Reproduction
```python
pipe = StableDiffusion3InpaintPipeline.from_pretrained(xxx)
pipe.scheduler = EulerAncestralDisc…