SHI-Labs / Prompt-Free-Diffusion

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024

https://arxiv.org/abs/2305.16223

SHI-Labs/Prompt-Free-Diffusion Issues

Multi GPU
Updated 3 months ago
Error, Where can I find the error log?
Updated 6 months ago1
Can this do promptless outpainting and inpainting like Adobe's Generative Fill?
Closed 7 months ago1
Incorrect implementation of self-attention
Updated 7 months ago
Query regarding image resolution for SeeCoder during training
Updated 8 months ago
VTON examples
Closed 10 months ago1
Inpainting results
Updated 10 months ago1
Do you have one SeeCoder that provides alignment with T5 rather than CLIP?
Updated 10 months ago3
Can we know the mapping (pixel mapping) from the output to the input image ?
Updated 10 months ago
in-house model
Closed 10 months ago1
Will you guys make an extension for automatic webui?
Closed a year ago1
Training code
Updated a year ago5
make training_dataset
Updated a year ago1
One reference image one model？
Closed a year ago1
text control
Updated a year ago1
how to train seecoder?
Closed a year ago3
Error when loading seecoder : Error(s) in loading state_dict for PromptFreeDiffusion_with_control: Missing key(s) in state_dict:
Closed a year ago1
Virtual Try-On testing on demo
Closed a year ago6
How to convert and use ckpt sd models with prompt free diffusion
Closed a year ago1
anime results is strange
Closed a year ago1
[Question] Pre-computed unconditional embeddings
Closed a year ago1
cuda.Out Of Memory
Closed a year ago2
The Huggingface Demo seems to have an error.
Closed a year ago1