UniControl
UniControl copied to clipboard
salesforce
Unified Controllable Visual Generation Model
function [``log_images``](https://github.com/lighten001/UniControl/blob/472c6cd347df2d2bccba3875d66d27946e847290/cldm/cldm.py#L366) will call ``get_input`` (which is the second time be called) on train batch end ```python z, c = self.get_input(batch, self.first_stage_key, bs=N) ``` so ``batch['text']`` will add ``[self.mapping_task[task_name]]`` twice...
Hi, the paper claimed "We have additionally collected a testing dataset for evaluation with 100-300 image condition-prompt triplets for each task. The source data is collected from Laion and COCO."...
I have thoroughly reviewed both your paper and the associated code. In the paper, it is mentioned that the model was trained on nine tasks. However, upon examining the code,...
That's definitely an impressive work! I'm trying to reproduce some results on inpainting task and had some concern about the data_parallel mode. Referring to the codes, batch_size is 4 for...
With the newer versions of pytorch the import: `from pytorch_lightning.utilities.distributed` becomes `from pytorch_lightning.utilities.rank_zero`
Combinations are not provided in Gradio's inference example，I want how to do conditional combinations？ 
# prepare chekpoint as original wa # 1 start : python app/gradio_multcontrol.py below are some samples~
Hello, I'm aiming to incorporate textual inversion into your impressive project. To start, my initial objective is to extract the stable diffusion weights from the unicontrol_v1.1.ckpt model and then load...
