hohonu-vicml / directeddiffusion Goto Github PK
View Code? Open in Web Editor NEWDirected Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)
Home Page: https://hohonu-vicml.github.io/DirectedDiffusion.Page/
Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)
Home Page: https://hohonu-vicml.github.io/DirectedDiffusion.Page/
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.
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]
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!
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!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.