Comments (8)
Hi,
What model and scheduler do you use? Do you use my examples?
If your code is short and you can share it, it will be easier for me to help :)
from renoise-inversion.
hi, I use:
model_type = Model_Type.SDXL
scheduler_type = Scheduler_Type.DDIM
I didn't modify anything in inversion_example_sdxl.py
.
from renoise-inversion.
hi, @garibida , I've also test inversion_example_turbo.py
and get similar fail results like:
However, I test inversion_example_sd.py
, get successful results.
The problem seems to be present in the SDXL model. Would you please check it?
Thank you.
from renoise-inversion.
Hi,
Did you use the environment.yaml or requirements.txt to create your environment? I created multiple environments and I wasn't able to reproduce this issue...
from renoise-inversion.
I had the same problem initially using my own environment and libraries, but creating the environment using environment.yaml
solved the issue. Strange that slightly different versions of pytorch/diffusers can cause the model to fail completely.
from renoise-inversion.
It's related to diffusers version. A newer version has some differences.
from renoise-inversion.
I found the reason. The core difference is in the pipeline_stable_diffusion_xl_img2img.py between 0.24.0 and latest versions. You can load the pipeline from 0.24.0 and then everything goes well.
To be more clear, there is a typo in 0.24.0, and it has been fixed in following updates.
In latest version,
timesteps, num_inference_steps = self.get_timesteps(
num_inference_steps,
strength,
device,
denoising_start=self.denoising_start if denoising_value_valid(self.denoising_start) else None,
)
in 0.24.0
timesteps, num_inference_steps = self.get_timesteps(
num_inference_steps,
strength,
device,
denoising_start=self.denoising_start if denoising_value_valid else None,
)
The denoising_start is different, which leads to different timesteps and noisy results.
from renoise-inversion.
@haofanwang hi, your answer perfectly solved my question, thank you!
I found the reason. The core difference is in the pipeline_stable_diffusion_xl_img2img.py between 0.24.0 and latest versions. You can load the pipeline from 0.24.0 and then everything goes well.
To be more clear, there is a typo in 0.24.0, and it has been fixed in following updates.
In latest version,
timesteps, num_inference_steps = self.get_timesteps( num_inference_steps, strength, device, denoising_start=self.denoising_start if denoising_value_valid(self.denoising_start) else None, )
in 0.24.0
timesteps, num_inference_steps = self.get_timesteps( num_inference_steps, strength, device, denoising_start=self.denoising_start if denoising_value_valid else None, )
The denoising_start is different, which leads to different timesteps and noisy results.
from renoise-inversion.
Related Issues (9)
- Code Release, please. HOT 1
- Issue with Image Reconstruction Using LCM Scheduler HOT 2
- Inversion with guidance scale > 1.0 HOT 5
- Configuration for models other than SDXL Turbo HOT 1
- Not working with SD15 and SD21 HOT 1
- How do I find zT with only ddim inversion without renoise? HOT 4
- I have a question about the prev_sample calculation process of the MyDDIMScheduler class. HOT 1
- Output has NaN HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from renoise-inversion.