ShihaoZhaoZSH/LaVi-Bridge
[ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation
PythonMIT
Issues
- 1
Train loss problem
#16 opened by CnFaker - 4
Error run inference t5_unet
#12 opened by NguyenNhoTrung - 0
Are there plans to release the weights for a LLAMA-to-PixArt Transformer adapter?
#15 opened by jamesBaker361 - 1
Training data preprocessing
#14 opened by lshymfl - 3
"nan" loss
#13 opened by tanshuai0219 - 2
residual connection
#11 opened by tanshuai0219 - 9
lora weight
#10 opened by tanshuai0219 - 2
LLAMA2 version
#9 opened by tanshuai0219 - 6
sdxl support?
#1 opened by DataCTE - 2
Use CLIP as text encoder
#8 opened by Espere-1119-Song - 1
train process problem
#6 opened by CS123n - 1
only use lora on unet or pixart?
#7 opened by CS123n - 1
- 1
llama-2-7b no config.json file error
#4 opened by habanerogossip - 1
- 1