tencent-ailab/PCDMs
Implementation code:Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Jupyter NotebookApache-2.0
Issues
- 1
I cannt get the right model
#27 opened by LucasShi1101 - 1
stage3测试问题
#25 opened by 1llss - 3
It does not work with custom poses or different poses other than the pair given in the example.
#21 opened by adityapandey9 - 1
About normalized_pose_txt.zip
#20 opened by rootpine - 1
How big is this model ??
#17 opened by complete-dope - 4
Where are the pose images?
#14 opened by xiechun-tsukuba - 1
第一阶段训好的先验模型是否在代码中没有用到?
#22 opened by hrz2000 - 8
Stage3 生成的图片有噪声
#23 opened by RuijieH - 0
- 6
Problems with the Weight of resolution 256 stage2
#24 opened by LOSKIw - 1
每阶段大概的训练时间是多长呢
#9 opened by EveningLin - 3
for the issues of pcdms_demo.ipynb
#19 opened by tonywang-sh - 1
- 1
Weights file seems missing
#18 opened by complete-dope - 3
- 3
- 4
请问有复现原论文Table2,关于reid map的代码么
#10 opened by shijie2016 - 0
求问有人跑通了代码么
#12 opened by jyangliu - 0
请问Stage1中使用的CLIP Image Encoder模型是哪一个?
#11 opened by jyangliu - 1
Is use OpenCLIP ViT-H/14 in demo?
#8 opened by thinkyang88 - 3
demo result wrong?
#7 opened by thinkyang88 - 2
tch: - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
#6 opened by I8Robot - 3
- 1
When will you release the code?
#2 opened by HaroldChen19 - 1
Config file
#3 opened by xiechun-tsukuba - 1
Code releaed
#1 opened by zobwink - 1
About the resolution
#4 opened by Maram-Helmy