Comments (4)
@hkunzhe if you one GPUs, you can't use deepspeed, in fact, we only has very small Trainable parameters, deepspeed has a small effect for the training speed. For deepspeed config, you can use this https://github.com/huggingface/accelerate/tree/main/examples/deepspeed_config_templates
Thanks for your reply! I got it!
from ip-adapter.
@bonlime hi, thank you for your interest in our work. The face-conditioned model is a experimental version, hence we're still working on improving it, we would like to train similar model for SDXL in the future. For IP-Adapter of sd1.5, we trained on a single machine with 8 V100 GPU, it took about 9 days for 1M steps. But as we observe, training about 200k steps can get good results.
for your ideas:
- We using the final CLIP embeddings like DALLE2, it can represent the content and style of the image. as discussed in 4.4.2 of our paper, we made a comparison of fine-grained features and global Features.
- The text encoding, clip embeddings is computed fast, so we don't cache them. Deepspeed is supported in accelerate https://github.com/huggingface/accelerate#launching-training-using-deepspeed
- you are right. In the training, we can segment the face as the condition, which will reduce the affect of background. Or, we can add attention score constraint in the training.
from ip-adapter.
@bonlime hi, thank you for your interest in our work. The face-conditioned model is a experimental version, hence we're still working on improving it, we would like to train similar model for SDXL in the future. For IP-Adapter of sd1.5, we trained on a single machine with 8 V100 GPU, it took about 9 days for 1M steps. But as we observe, training about 200k steps can get good results.
for your ideas:
- We using the final CLIP embeddings like DALLE2, it can represent the content and style of the image. as discussed in 4.4.2 of our paper, we made a comparison of fine-grained features and global Features.
- The text encoding, clip embeddings is computed fast, so we don't cache them. Deepspeed is supported in accelerate https://github.com/huggingface/accelerate#launching-training-using-deepspeed
- you are right. In the training, we can segment the face as the condition, which will reduce the affect of background. Or, we can add attention score constraint in the training.
Does DeepSpeed help with single GPU training? Can you share the DeepSpeed config file for ZeRO stage 2 as mentioned in your paper?
from ip-adapter.
@hkunzhe if you one GPUs, you can't use deepspeed, in fact, we only has very small Trainable parameters, deepspeed has a small effect for the training speed. For deepspeed config, you can use this https://github.com/huggingface/accelerate/tree/main/examples/deepspeed_config_templates
from ip-adapter.
Related Issues (20)
- ImportError: cannot import name 'ValidationInfo' from 'pydantic' HOT 1
- Traning Code for SD2.1
- How should I go about training the ip adapter plus sdxl for inpainting by providing it a reference image ?
- How to use ip-adapter-faceid-portrait_sdxl.bin
- 一些训练增强方式细节的请教~ HOT 2
- hunyuan-dit version of the ip adapter
- Question about "ip-adapter_sd15_light.safetensors"
- Question - How to generate depth map image
- How to generate side view human accurately
- A preprocessor ip adapter clip sd15 is missing HOT 1
- Question on adding IP-Adapter on SD3
- How should I resolve an error when I reach this step? HOT 1
- is it" ipadapter mad scientist "does not work in 1.5model?
- question about cross attention
- questions about training
- Generating undersaturated images
- train IP-Adapter with Kolors?
- train IP-Adapter based on Kolors ?
- Question about the [Scale] Parameter
- Custom Foreground in Custom Background using 'SD-XL Inpaint'
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 ip-adapter.