fractaldna22

+ it does animations "A girl walking on the sidewalk in slow motion" produces iterations of a girl actually walking in slow motion. this has never been mentioned by Dall-E...

Yes totally. And I don't see the words "white background" in the prompt On Wed, Apr 7, 2021, 10:11 AM afiaka87 ***@***.***> wrote: > [image: image] > > vqvae >...

the results in Lora training saves the images to the log folder and can only be seen in WandB. I hate that and i hate tensorboard and all of that....

You don't need to do image_features /= image_features.norm(dim=-1, keepdim=True) text_features /= text_features.norm(dim=-1, keepdim=True) if you're using cosine_similarity. torch.cosine_similarity(x, y) already normalizes the inputs, by nature of cosines. To normalize via...

They only do x /= x.norm() when they use similarity = (100.0 * image_features @ text_features.T)[0].cpu().numpy() since this isnt actualy cosine similarity, its x @ y.T, thus x and y...

i cant even get one single repo to work lol. sucks i really was looking forward to this for my psytrance folders. im a dj not a programmer T_T

> > How do you get the module to use the value that you've extracted? > > Similar to how you pass the cookie string value to the Bard.py script...

i still cant get it to work :( Im using the chatbot usecase, with ChatGPT-DIscord-Bot-1.5.1. By commenting out the errors and pasting in the SNlM0e directly instead of using the...

```python async def __get_snlm0e(self): # Find "SNlM0e":"" #if not self.session_id or self.session_id[-1] != ".": # raise Exception( # "__Secure-1PSID value must end with a single dot. Enter correct __Secure-1PSID value.",...

```python def select_figure(res): # Use some criteria to match the response with one of the figures # For example, you can use keywords, topics, tone, style, etc. # You can...