The directeddiffusion from hohonu-vicml

directeddiffusion's Issues

[email protected]: Permission denied (publickey).

Cloning into 'conditioned-diffusion'...
[email protected]: Permission denied (publickey).
fatal: Could not read from remote repository.

Please make sure you have the correct access rights
and the repository exists.

bad case

In the experiment, I changed 10 seeds, but most of the results were not good, and the generated object was not within the constraint of box. Is there any way to solve it?
The diffusers version I use is 0.14.0 and the SD version is 1.4.The seeds are [894358745378543,132344342112,32123134345651,54354465546545,5454645654654659,56945654664568,685345657659,56902343242342389,657454353453482,2483964026821236]

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

Hello, I'm really inspired by your outstanding work of Directed Diffusion. However, when I tried to run DDCmd.py, I got the following error:

Traceback (most recent call last):
  File "./bin/DDCmd.py", line 440, in <module>
    main()
  File "./bin/DDCmd.py", line 382, in main
    img = DirectedDiffusion.Diffusion.stablediffusion(
  File "/home/****/miniconda3/envs/nullptp/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/****/DirectedDiffusion/source/DirectedDiffusion/Diffusion.py", line 91, in stablediffusion
    latent = scheduler.add_noise(
  File "/home/****/.local/lib/python3.8/site-packages/diffusers/schedulers/scheduling_lms_discrete.py", line 187, in add_noise
    sigmas = self.match_shape(self.sigmas[timesteps], noise)
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

When I tried to fix it by changing File "/home/****/DirectedDiffusion/source/DirectedDiffusion/Diffusion.py", line 91:

torch.tensor([scheduler.timesteps[t_start]], device=device, dtype=torch.float16)
->
torch.tensor([scheduler.timesteps[t_start]], device=device, dtype=torch.int)

I got:

Traceback (most recent call last):
  File "./bin/DDCmd.py", line 440, in <module>
    main()
  File "./bin/DDCmd.py", line 382, in main
    img = DirectedDiffusion.Diffusion.stablediffusion(
  File "/home/****/miniconda3/envs/nullptp/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/****/DirectedDiffusion/source/DirectedDiffusion/Diffusion.py", line 91, in stablediffusion
    latent = scheduler.add_noise(
  File "/home/****/.local/lib/python3.8/site-packages/diffusers/schedulers/scheduling_lms_discrete.py", line 187, in add_noise
    sigmas = self.match_shape(self.sigmas[timesteps], noise)
IndexError: tensors used as indices must be long, byte or bool tensors

Looking forward to your answer! Thanks a lot!

Some functions showing in paper didn't find in code...

Hello! I've read your paper: 'Directed Diffusion: Direct Control of Object Placement through Attention Guidance'. I saw your method is to optim a learned weight vector 'a'∈ R_77−|P|−1. I'm interested about it , but I didn't find where it implemented in your code. I would like to know if you can provide your full code support. My email is [email protected]. Thanks a lot!

hohonu-vicml / directeddiffusion Goto Github PK

directeddiffusion's People

Contributors

Stargazers

Watchers

Forkers

directeddiffusion's Issues

[email protected]: Permission denied (publickey).

bad case

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

Some functions showing in paper didn't find in code...

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent