-
Hello.
PixelTiledKSampleUpscalerProviderPipe throws this error.
```
PixelTiledKSampleUpscalerProviderPipe throws this error.
Traceback (most recent call last):
File "E:\diffusion\Comfy…
-
I try to use clip text guidance instead of CFG in SD-Style, but the result seems not satisfatory, could u please help me find what's going wrong? Here is the code, I only change three lines in the fil…
-
Hi,
This is really a very good repo for learning stable diffusion from scratch. However, I found the missing scaling factor that should have been applied to latent $z$ before U-Net. It was said to …
-
您好我看您论文中说是使用Latent-diffusion的代码，我发现您的代码和[Latent-diffusion的官方代码](https://github.com/CompVis/latent-diffusion)相差很多。
1：能否告诉您使用的latent-diffusion代码的地址吗？
2：您使用的Latent-diffusion代码和官方的代码是等效的吗。
虽然问题很奇怪，但是这…
-
I read and was interested in your paper 'Scene Graph Conditioning in Latent Diffusion' that had the link to this repository for the models discussed but i was not able to find them in the repository. …
-
# ComfyUI Error Report
## Error Details
- **Node Type:** SamplerCustomAdvanced
- **Exception Type:** RuntimeError
- **Exception Message:** Boolean value of Tensor with more than one value is amb…
-
In ddim.py, is there any implementation of this todo part: deterministic forward pass?
if mask is not None:
assert x0 is not None
img_orig = self.model.q_sample(x0, …
-
在扩散模型浅空间中更新扰动，将潜在向量变为图片时，需要使用
def diffusion_step(model, latents, context, t, guidance_scale):
latents_input = torch.cat([latents] * 2)
noise_pred = model.unet(latents_input, t, encoder_hidd…
-
how to use the image y to be restored and the mask in the latent space? Can I use the VAE encoder to encode them into the latent space? Then, can I decode the final restored x back to pixel space usi…
-
My gpu is 2080ti22G, comfyui says the cuda does not support bf16, I have to set model_dtype as fp16, Then I keep getting "nan in lantents" error. the whole log is as follows:
2024-10-12 00:05:30,…