alibaba/animate-anything issues and pull requests

#61 - avoid confusion with pretrained model names.

Pull Request - State: closed - Opened by sculmh 9 months ago

#60 - support video2video for the SVD model

Pull Request - State: closed - Opened by sculmh 9 months ago

#59 - Support Google Colab

Pull Request - State: closed - Opened by dailingx 9 months ago

#58 - how to control motion magnitude

Issue - State: open - Opened by hw-liang 9 months ago - 1 comment

#57 - 请问 /webvid/webvid/data/40K.json 数据格式是什么样的？

Issue - State: open - Opened by cklogic 9 months ago - 1 comment

#56 - fix readme imgs

Pull Request - State: closed - Opened by sculmh 9 months ago - 1 comment

#55 - error: "AttributeError: 'DistributedDataParallel' object has no attribute 'enable_gradient_checkpointing'"

Issue - State: closed - Opened by shaowujie 9 months ago - 3 comments

#54 - train_svd.py error

Issue - State: closed - Opened by shaowujie 10 months ago - 2 comments

#53 - Set-of-Masks for Multiple Motion Guidance

Issue - State: open - Opened by HariWu1995 10 months ago - 1 comment

#52 - how to explain the mask loss?

Issue - State: closed - Opened by YujieOuO 10 months ago - 1 comment

#51 - Running python train.py with example/train_mask_motion.yaml, I get the warning

Issue - State: closed - Opened by xyxxmb 11 months ago - 1 comment

#50 - cache_latents error

Issue - State: closed - Opened by xyxxmb 11 months ago - 2 comments

#49 - How to setup dataset

Issue - State: closed - Opened by SwayStar123 11 months ago - 1 comment

#48 - docs: fix typos

Pull Request - State: closed - Opened by Leojc 11 months ago - 1 comment

#47 - Interference issue II

Issue - State: closed - Opened by liw8hz 12 months ago - 2 comments

#46 - Interference issue

Issue - State: closed - Opened by liw8hz 12 months ago - 1 comment

#45 - How is LORA used in fine-tuning?

Issue - State: closed - Opened by efzero 12 months ago - 1 comment

#44 - Finetuning animate-anything VRAM issue

Issue - State: closed - Opened by mylee95 12 months ago - 2 comments

#43 - Optimize: Ensure video saving FPS is consistent with input parameter

Pull Request - State: closed - Opened by dailingx 12 months ago

#42 - how can inference the trained SVD model

Issue - State: closed - Opened by senlin-ali 12 months ago

#41 - [BUG] 'mask' not found when dataset type is "video_json"

Issue - State: closed - Opened by yunkchen 12 months ago - 2 comments

#40 - fix seed not random when seed_textbox input with -1

Pull Request - State: closed - Opened by dailingx 12 months ago

#39 - How to prepare the training dataset?

Issue - State: closed - Opened by YujieOuO 12 months ago - 2 comments

#38 - Finetune SVD Lora？

Issue - State: closed - Opened by huangjch526 12 months ago - 1 comment

#37 - Fix text_encoder not on the GPU

Pull Request - State: closed - Opened by dailingx 12 months ago

#36 - When i finetune animate-anything，Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [8, 320]

Issue - State: closed - Opened by lion-ops 12 months ago - 1 comment

#35 - What does the variable frame_number mean?it is not defined

Issue - State: closed - Opened by lion-ops 12 months ago - 1 comment

#34 - Question about the hyper-parameters in finetune_unet function.

Issue - State: closed - Opened by phil329 12 months ago - 1 comment

#33 - Small range of motion

Issue - State: closed - Opened by senlin-ali about 1 year ago - 1 comment

#32 - Question about SVD finetuning result

Issue - State: open - Opened by buaacyw about 1 year ago - 1 comment

#32 - Question about SVD finetuning result

Issue - State: open - Opened by buaacyw about 1 year ago

#31 - This problem?

Issue - State: closed - Opened by waternight1029 about 1 year ago - 1 comment

#30 - Compatibility of pretrained checkpoint

Issue - State: closed - Opened by LucasChenLC about 1 year ago - 1 comment

#29 - ImportError: cannot import name 'HF_HOME' from 'huggingface_hub.constants'

Issue - State: closed - Opened by waternight1029 about 1 year ago - 2 comments

#28 - Update README.md

Pull Request - State: closed - Opened by Leojc about 1 year ago - 1 comment

#28 - Update README.md

Pull Request - State: closed - Opened by Leojc about 1 year ago - 1 comment

#27 - for svd: open more parameters, add gradio ui and fix error

Pull Request - State: closed - Opened by dailingx about 1 year ago

#27 - for svd: open more parameters, add gradio ui and fix error

Pull Request - State: closed - Opened by dailingx about 1 year ago

#26 - for svd: open more parameters, add gradio ui

Pull Request - State: closed - Opened by dailingx about 1 year ago - 1 comment

#26 - for svd: open more parameters, add gradio ui

Pull Request - State: closed - Opened by dailingx about 1 year ago - 1 comment

#25 - How to config lora.yaml

Issue - State: closed - Opened by howardgriffin about 1 year ago - 1 comment

#24 - Encountering "Tensor Shape Mismatch" Error during Training

Issue - State: closed - Opened by yvfengZhong about 1 year ago - 5 comments

#24 - Encountering "Tensor Shape Mismatch" Error during Training

Issue - State: closed - Opened by yvfengZhong about 1 year ago - 5 comments

#23 - ValueError: num_samples should be a positive integer value, but got num_samples=0

Issue - State: closed - Opened by dailingx about 1 year ago - 1 comment

#22 - Question about the training data

Issue - State: closed - Opened by YujieOuO about 1 year ago - 2 comments

#22 - Question about the training data

Issue - State: closed - Opened by YujieOuO about 1 year ago - 2 comments

#21 - VRAM Requirements to Fine-tune SVD

Issue - State: closed - Opened by mlfarinha about 1 year ago - 1 comment

#21 - VRAM Requirements to Fine-tune SVD

Issue - State: closed - Opened by mlfarinha about 1 year ago - 1 comment

#20 - RuntimeError while running train_svd

Issue - State: closed - Opened by sam-motamed about 1 year ago - 8 comments

#19 - Finetune SVD with webvid

Issue - State: closed - Opened by JunruiXiao about 1 year ago - 1 comment

#18 - Is there a typo?

Issue - State: closed - Opened by westfish about 1 year ago - 1 comment

#17 - animate_anything_svd_v1.0

Issue - State: closed - Opened by YujieOuO about 1 year ago - 7 comments

#17 - animate_anything_svd_v1.0

Issue - State: closed - Opened by YujieOuO about 1 year ago - 7 comments

#16 - convert validation_data.prompt_image mode from RGBA to RGB

Pull Request - State: closed - Opened by dailingx about 1 year ago - 1 comment

#15 - convert validation_data.prompt_image mode from RGBA to RGB

Pull Request - State: closed - Opened by dailingx about 1 year ago - 1 comment

#14 - question about some implementation details

Issue - State: closed - Opened by hw-liang about 1 year ago - 3 comments

#13 - Update requirements.txt for imageio

Pull Request - State: closed - Opened by dailingx about 1 year ago - 2 comments

#13 - Update requirements.txt for imageio

Pull Request - State: closed - Opened by dailingx about 1 year ago - 2 comments

#12 - Error when training SVD without mask.

Issue - State: closed - Opened by yunkchen about 1 year ago - 1 comment

#12 - Error when training SVD without mask.

Issue - State: closed - Opened by yunkchen about 1 year ago - 1 comment

#11 - Why do you re-prepare the models after saving the states?

Issue - State: closed - Opened by yutaocui about 1 year ago - 1 comment

#11 - Why do you re-prepare the models after saving the states?

Issue - State: closed - Opened by yutaocui about 1 year ago - 1 comment

#10 - Update README.md

Pull Request - State: closed - Opened by eltociear about 1 year ago

#10 - Update README.md

Pull Request - State: closed - Opened by eltociear about 1 year ago

#9 - Create a loop

Issue - State: closed - Opened by C00reNUT about 1 year ago - 1 comment

#8 - how much GPU RAM does inference require?

Issue - State: closed - Opened by TruthSearcher about 1 year ago - 1 comment

#8 - how much GPU RAM does inference require?

Issue - State: closed - Opened by TruthSearcher about 1 year ago - 1 comment

#7 - "This config requires around 80G GPU RAM"

Issue - State: closed - Opened by ninjasaid2k about 1 year ago - 1 comment

#7 - "This config requires around 80G GPU RAM"

Issue - State: closed - Opened by ninjasaid2k about 1 year ago - 1 comment

#6 - 你好，用https://cloudbook-public-production.oss-cn-shanghai.aliyuncs.com/animation/animate_anything_svd_v1.0.tar权重,eval模式，会挂

Issue - State: closed - Opened by ersanliqiao about 1 year ago - 2 comments

#6 - 你好，用https://cloudbook-public-production.oss-cn-shanghai.aliyuncs.com/animation/animate_anything_svd_v1.0.tar权重,eval模式，会挂

Issue - State: closed - Opened by ersanliqiao about 1 year ago - 2 comments

#5 - typeError: _set_gradient_checkpointing() got an unexpected keyword argument 'value'

Issue - State: closed - Opened by JornyWan about 1 year ago - 4 comments

GitHub / alibaba/animate-anything issues and pull requests