We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hello , Why i am getting down_cross Key error while running prompt-to-prompt_stable.ipynb? This is the case with local edit :
prompts = ["A painting of a squirrel eating a burger", "A painting of a lion eating a burger"] lb = LocalBlend(prompts, ("squirrel", "lion")) controller = AttentionReplace(prompts, NUM_DIFFUSION_STEPS, cross_replace_steps={"default_": 1., "lion": .4}, self_replace_steps=0.4, local_blend=lb) _ = run_and_display(prompts, controller, latent=x_t, run_baseline=False)
KeyError Traceback (most recent call last) in <cell line: 7>() 5 cross_replace_steps={"default_": 1., "lion": .4}, 6 self_replace_steps=0.4, local_blend=lb) ----> 7 _ = run_and_display(prompts, controller, latent=x_t, run_baseline=False)
5 frames in call(self, x_t, attention_store) 3 def call(self, x_t, attention_store): 4 k = 1 ----> 5 maps = attention_store["down_cross"][2:4] + attention_store["up_cross"][:3] 6 maps = [item.reshape(self.alpha_layers.shape[0], -1, 1, 16, 16, MAX_NUM_WORDS) for item in maps] 7 maps = torch.cat(maps, dim=1)
KeyError: 'down_cross'
I have T4 GPU enabled in google colab pro.
Regards, S
The text was updated successfully, but these errors were encountered:
I encountered the same problem. Did you solve it?
Sorry, something went wrong.
me too, any ideas? thx.
No branches or pull requests
Hello ,
Why i am getting down_cross Key error while running prompt-to-prompt_stable.ipynb?
This is the case with local edit :
prompts = ["A painting of a squirrel eating a burger",
"A painting of a lion eating a burger"]
lb = LocalBlend(prompts, ("squirrel", "lion"))
controller = AttentionReplace(prompts, NUM_DIFFUSION_STEPS,
cross_replace_steps={"default_": 1., "lion": .4},
self_replace_steps=0.4, local_blend=lb)
_ = run_and_display(prompts, controller, latent=x_t, run_baseline=False)
0%
0/51 [00:00<?, ?it/s]
KeyError Traceback (most recent call last)
in <cell line: 7>()
5 cross_replace_steps={"default_": 1., "lion": .4},
6 self_replace_steps=0.4, local_blend=lb)
----> 7 _ = run_and_display(prompts, controller, latent=x_t, run_baseline=False)
5 frames
in call(self, x_t, attention_store)
3 def call(self, x_t, attention_store):
4 k = 1
----> 5 maps = attention_store["down_cross"][2:4] + attention_store["up_cross"][:3]
6 maps = [item.reshape(self.alpha_layers.shape[0], -1, 1, 16, 16, MAX_NUM_WORDS) for item in maps]
7 maps = torch.cat(maps, dim=1)
KeyError: 'down_cross'
I have T4 GPU enabled in google colab pro.
Regards,
S
The text was updated successfully, but these errors were encountered: