cientgu/InstructDiffusion
PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
PythonNOASSERTION
Issues
- 0
Diffusers Inplyment Request
#27 opened by Bili-Sakura - 4
- 0
checkpoint
#26 opened by ybx193670 - 0
- 1
No web demo
#15 opened by sedol1339 - 1
LOSS is not declinig
#24 opened by YerongLi - 3
Checkpoint for Training
#12 opened by wusize - 1
- 0
prompt about detection task
#23 opened by Yangyangziovo - 0
two checkpoints, which is better?
#19 opened by zhuzhuzhu001 - 0
- 0
demo broken No interface is running right now
#17 opened by huangjch526 - 0
- 3
prompt about classification and detection
#4 opened by wenqsun - 0
Is the IEIW dataset open source?
#14 opened by AFeng-x - 1
Will the code for evaluation be released?
#11 opened by tingxueronghua - 8
Supported training phase
#8 opened by SxJyJay - 0
- 2
- 1
- 6
Can this work output a full-image segmentation mask (non-transparent), rather than a semi-transparent mask specific to an object?
#3 opened by edwardyehuang - 4
- 3
Will the proposed datasets be released ?
#6 opened by Zeqiang-Lai - 1
How to use Web demo
#5 opened by Xushuolin - 1
Instruction Template
#2 opened by sauradip