LeonJoe13

> with > Hi, thank you for your interest in our work. Can I ask what you have changed? This result seems abnormal, it looks like it might be a...

if I follow your env, it can't work in NVIDIA-SMI 470.182.03 Driver Version: 470.182.03 CUDA Version: 11.8 my env is : absl-py 2.0.0 aiohttp 3.9.1 aiosignal 1.3.1 asttokens 2.4.1 async-timeout...

> > > video 1 looks pretty good 👍 ！how many steps you trained the stage 1 ？ I trained 13000 steps but still can‘t control the pose :( ....

> Hello, @guoqincode! The samples in the test set worked fine, but with pure black clothes, I often got black and white results. Have you ever run into similar problems....

> > I feel strange, I am at 512 resolution, single card bs=8. > > 当我把"sample_n_frames: 16mixed_precision_training" and "enable_xformers_memory_efficient_attention"设置为True后，可以正常跑起来。但是还有个问题，在train_hack.py里设置poseguider的输出为320维（poseguider = PoseGuider(noise_latent_channels=320)），但是在推理的时候python3 -m pipelines.animation_stage_1 --config configs/prompts/animation_stage_1.yaml，加载poseguider模型时，设置的channel是4，model = PoseGuider(noise_latent_channels=4)，而且在后续的pipeline 里面使用的方式对应的也是channel为4的情况（latent_model_input = self.scheduler.scale_model_input(latent_model_input,...

> > > I feel strange, I am at 512 resolution, single card bs=8. > > > > > > 当我把"sample_n_frames: 16mixed_precision_training" and "enable_xformers_memory_efficient_attention"设置为True后，可以正常跑起来。但是还有个问题，在train_hack.py里设置poseguider的输出为320维（poseguider = PoseGuider(noise_latent_channels=320)），但是在推理的时候python3 -m pipelines.animation_stage_1 --config configs/prompts/animation_stage_1.yaml，加载poseguider模型时，设置的channel是4，model...