-
Hi!
First, thanks for your work!
I tried to interpolate between 2 faces in the dlatent space (18, 512) and the result seems to be not as meaningful as it is if interpolating between 2 vectors i…
-
As noted in https://github.com/llvm/circt/pull/5009, https://github.com/llvm/circt/pull/5025, `seq.firmem` was introduced to initially help factoring out memory handling in the FIRRTL-to-HW pass. Once…
-
Hello,
Firstly, just wanted to state that this is a great repo with a very understandable code base!
I seem to be getting extremely low MIG / AAM scores (around 1e-3 to 1e-2) when training with …
-
It seems that some code, such as the code for SVD decomposition visualization, is not included in the publicly released code. Looking forward to it being open-sourced!
-
Hello, I've been learning your code lately, and now I can generate a watermark image randomly according to the prompts, but I want to generate the original image and the watermark image of the exact s…
-
Hello, I noticed that you are using CCM as the latent image for ldm fine-tune, but the channel for CCM is 3 and the original latent image from VAE is 4. Did you modify the input layer of the model? Be…
LTT-O updated
5 months ago
-
-
The division of the recording API from the exporter API prevents many types of data analysis. Ideally, the exporter should be allowed to "subscribe" to events pushed at the record API (e.g. observe t…
-
Hi,
First of all amazing work!, the generated images have great quality. I tried running it on my computer and it seems like the encoder doesn't learn properly. I tried a few things but couldn't fi…
-
Looking for pointers to get started on modifying the conditioning code below to include conditioning on an image along with text.
```
videos = torch.randn(2, 3, 5, 32, 32) # video (batch, channels…