Comments (3)
I used 10 pictures of a person's face to fine-tune the model, but the results don't seem to be as good as described in the README.md. Can you provide more details on how to train the model?
from custom-diffusion.
Hi, thanks for your interest in this work.
You can find more detailed instructions for fine-tuning on faces in the issue here. These results are with regularization images obtained using clip-retrieval only.
Training on faces is better with fine-tuning all cross-attention parameters and requires longer training time with more images compared to other categories.
Hopefully, this should help in getting better results.
from custom-diffusion.
@nupurkmr9 ,Thank you for your prompt response and for sharing the detailed instructions for fine-tuning on faces. I appreciate your help.
I'm happy to inform you that I was able to deal with the issue. I followed your instructions and fine-tuned all cross-attention parameters, which required longer training time with more images compared to other categories, as you mentioned. The results are much better now, and I'm satisfied with the performance.
Thanks again for your support:)
from custom-diffusion.
Related Issues (20)
- No module named 'diffusers.models.cross_attention' HOT 1
- Errors in using diffuser version HOT 3
- A question for the regularization captions HOT 1
- questions about crossattn in CustomDiffusionAttnProcessor
- Question about the cross attention HOT 1
- ImportError: cannot import name 'insecure_hashlib' from 'huggingface_hub.utils' 怎么解决? HOT 1
- Hi, How toMultiple-Concept Fine-tuning for DreamBooth?
- if it OK with no regularization? my results don't have any consistancy with reference images. HOT 3
- Ours (w/fine-tune all) ? HOT 2
- OOM while running sample.py HOT 4
- why my optimization based weights merging is not work? HOT 4
- Is it possible to train multi joint training with SDXL? diffusers_training_sdxl.py seems impossible for multi joint training. HOT 2
- Question about loss on valid image region during training HOT 1
- Missing text prompts? HOT 2
- Does the diffusers version now work properly? HOT 3
- why the results produced by the model training and verification are inconsistent with the results I test using the saved model weights? HOT 1
- Evaluation:where is the “prompts.json”file?
- Unable to retrieve the image used for regularization. HOT 1
- Is this version trained with lora? HOT 1
- Tensors not Updated after Training 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 custom-diffusion.