showlab/Tune-A-Video

Issues

• Pose Control Implementation

  #54 opened a year ago by Shr1ftyy
  7

• Bug of background

  #99 opened a month ago by xiangxinhello
  1

• Question about fine-tuning.

  #59 opened a year ago by RuoyuFeng
  7

• GOOD LUCK

  #98 opened a month ago by xiangxinhello
  0

• NotImplementedError: No operator found for `memory_efficient_attention_forward`

  #97 opened a month ago by shihzenq
  0

• ValueError: Less than two GPU ids were configured and tried to run on on multiple GPUs. Please ensure at least two are specified for `--gpu_ids`, or use `--gpu_ids='all'`.

  #96 opened 2 months ago by marti844
  0

• The specified procedure could not be found.

  #95 opened 2 months ago by 23Rj20
  1

• ARCHIVE THIS PROJECT - use this instead - https://ar5iv.labs.arxiv.org/html/2305.08850

  #94 opened 3 months ago by johndpope
  0

• AttributeError: 'AttentionBlock' object has no attribute 'to_k'

  #92 opened 3 months ago by saran-eizen
  0

• Question about training loss.

  #86 opened 9 months ago by Guanys-dar
  1

• the datasets of Fine-Tuning network?which?

  #91 opened 4 months ago by henbucuoshanghai
  1

• RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one.

  #79 opened a year ago by chenglinh
  2

• 如何多卡训练

  #81 opened 10 months ago by chongjg
  1

• server socket fault

  #90 opened 5 months ago by qy0720
  0

• 请问下下载模型报错，如何解决？

  #52 opened a year ago by Fangshaohua8
  3

• Bad results generated from stable-diffusion-v2-1

  #85 opened 9 months ago by wanghao14
  1

• RecursionError: maximum recursion depth exceeded in comparison

  #89 opened 7 months ago by xiefan233
  0

• Colab Error: "Error no file named diffusion_pytorch_model.bin found in directory outputs/man-skiing"

  #88 opened 7 months ago by zainkazi
  0

• No such file or directory: './outputs/man-skiing/inv_latents/ddim_latent-500.pt'

  #87 opened 8 months ago by anarabiyev
  0

• RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`, and by making sure all `forward` function outputs participate in calculating loss

  #78 opened a year ago by cuiliyuan121
  1

• AttributeError: 'AttentionBlock' object has no attribute 'to_q'

  #82 opened 10 months ago by userkenny
  1

• samples文件夹里面出的图是全黑的

  #72 opened a year ago by Jamie-Cheung
  3

• Is it possible to train only `ddim_inv_latent` and reuse Unet3d model from AnimateDiff?

  #84 opened 9 months ago by actionless
  0

• diffusers version conflicts

  #83 opened 10 months ago by userkenny
  0

• Hands + face Guide

  #80 opened a year ago by p0mad
  0

• What does this mean: “encoder_hidden_states = encoder_hidden_states”?

  #77 opened a year ago by XuejiFang
  0

• DDIM inversion or ramdon noise?

  #73 opened a year ago by tszFung-gz
  2

• ValueError: Using torch.compile requires PyTorch 2.0 or higher

  #76 opened a year ago by OLDDDDDDD
  0

• unet.down_blocks does not seem to be updating

  #69 opened a year ago by czk32611
  3

• ValueError: unknown mid_block_type : UNetMidBlock2DCrossAttn

  #71 opened a year ago by piano-accordion
  1

• Tensor type mismatch during training and validation

  #65 opened a year ago by Jeff-LiangF
  1

• Autoregressive

  #68 opened a year ago by dlutzzw
  1

• about deflicker

  #67 opened a year ago by suzhenghang
  1

• Request for release of selected DAVIS videos and associated captions & prompts

  #74 opened a year ago by knightyxp
  1

• Is all the model in this code is the new versions?

  #75 opened a year ago by minhhieu50050
  1

• Image+Text guided video editing

  #70 opened a year ago by rakesh-reddy95
  2

• Lora weights

  #66 opened a year ago by rakesh-reddy95
  6

• Warning from the dancing man‘s fans, true ikun!!!

  #63 opened a year ago by JoeZhang01
  1

• Unexpected results with Stable diffusion 2.1

  #64 opened a year ago by jaykim9870
  1

• why the sample generated by accelerate command looks much better than the gif generated by the inference script

  #60 opened a year ago by heptagonnnn
  1

• ValueError: unknown mid_block_type : UNetMidBlock2DCrossAttn on model trained with dreambooth

  #56 opened a year ago by ypsl
  5

• how to use DreamBooth

  #62 opened a year ago by longglecc
  1

• imageio version problem

  #61 opened a year ago by longglecc
  2

• what's the meaning of 'n_sample_frames' and 'video_length', should they be same?

  #58 opened a year ago by overfiter
  3

• Why is the performance of my model becoming worse as I continue training?（为啥我的模型效果越训越差？）

  #57 opened a year ago by zhangtao22
  1

• video prediction

  #55 opened a year ago by JWFanggit
  2

• Something error happened In the training step ，see the picture.

  #48 opened a year ago by Virgilseed
  1

• help，请问这个怎么解决？

  #51 opened a year ago by novazhjun
  1

• attention_mask is None during training

  #53 opened a year ago by liqq010
  1

• How to train with video size 256*256

  #50 opened a year ago by LiRunyi2001
  3