-
## 論文タイトル（原文まま）
Scalable Diffusion Models with Transformers
## 一言でいうと
従来のU-Netを代替するトランスフォーマーベースの新しい拡散モデル「Diffusion Transformers (DiTs)」を導入し、計算効率を高めつつ画像生成の品質を向上させる手法を提案。
### 論文リンク
[https://www…
-
I noticed some subtle differences in the implementation of your UNet and the one in this repo: https://github.com/johschmidt42/PyTorch-2D-3D-UNet-Tutorial.
Basically, the batch normalization is pe…
-
### Describe the bug
I try to finetune a SDXL model. But meet same questions.
I can not resume from a checkpoint model and the error is shown as follows:
[rank0]: load_checkpoint_in_model(
…
-
Thank you for your excellent work. I have a question after reading. The paper does not explain the hyperparameter n in detail. Could you please explain why n is applied when hidden_states = 1280, but …
-
How to implement img2img?
` sigmas = self.get_sigmas_karras(steps).to(self.device)
print(type(init_image))
# latents
# noise = torch.randn((size[0], 4, size[1] // 8,…
-
Run python test_pasd_sdxl.py
Traceback (most recent call last):
File "D:\PASD\test_pasd_sdxl.py", line 319, in
main(args)
File "D:\PASD\test_pasd_sdxl.py", line 206, in main
pipeline…
-
**Is your feature request related to a problem? Please describe.**
have a demo for UNet running on device via TTNN
**Describe the solution you'd like**
Have a demo of UNet carvana and/or UNet Bra…
-
zaqai updated
2 weeks ago
-
What comes up when you are using the official ControlNet model:
Traceback (most recent call last):
File "D:\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = ge…
-
ValueError: Cannot load from D:\workspace\ai\ComfyUI\models\diffusers\Kolors because the following keys are missing:
encoder_hid_proj.weight, encoder_hid_proj.bias.
Please make sure to pass `low_…