weijiawu / paradiffusion Goto Github PK
View Code? Open in Web Editor NEWOfficial code for 'Paragraph-to-Image Generation with Information-Enriched Diffusion Model'
Official code for 'Paragraph-to-Image Generation with Information-Enriched Diffusion Model'
Wrote in the paper:
For the diffusion model, we follow SDXL [23] and use a Unet of 1.3B parameters to learn the latent Gaussian noise.
But in the released model unet config file:
"block_out_channels": [ 384, 768, 1152, 1536],
Could I assume that you finetune on SDXL actually and only release the 1.x version?
Will the training code be released?
In your ParaPrompts_400.csv, I can only find the image name, category and prompt. The image source is missing, I don't know where the images come from, can you provide more information?
What is the size of LLaMA v2 you use? 7B or 13B or 70B? Does the size matter?
When I train stage 1, where the llama2 is frozen and linear layer+unet are trainable, I get "nan" loss after few hundreds steps.
Could u give me some advices?
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.