shunk031/training-free-structured-diffusion-guidance
🤗 Unofficial huggingface/diffusers-based implementation of the paper "Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis".
PythonApache-2.0
Issues
- 3
- 1
RuntimeError: Input type (float) and bias type (c10::Half) should be the same
#10 opened by howardgriffin - 2
The implementation is wrong
#11 opened by elvisnava - 2
Implementation doubt
#9 opened by helia95 - 1
Using in Stable-Diffusion-gRPCServer
#6 opened by hafriedlander - 2
- 1
CI is failing due to OOM
#3 opened by shunk031