AILab-CVC/VideoCrafter issues and pull requests

#93 - Version using CLIP from transformers

Issue - State: open - Opened by HyelinNAM 3 days ago

#93 - Version using CLIP from transformers

Issue - State: open - Opened by HyelinNAM 3 days ago

#92 - cuda, mps, cpu

Issue - State: open - Opened by mattiaskjellsson 17 days ago

#92 - cuda, mps, cpu

Issue - State: open - Opened by mattiaskjellsson 17 days ago

#91 - training loss

Issue - State: open - Opened by dmmSJTU 29 days ago

#91 - training loss

Issue - State: open - Opened by dmmSJTU 29 days ago

#90 - RuntimeError: The shape of the 2D attn_mask is torch.Size([77, 77]), but should be (1, 1).

Issue - State: open - Opened by kasoushu about 1 month ago - 1 comment

#90 - RuntimeError: The shape of the 2D attn_mask is torch.Size([77, 77]), but should be (1, 1).

Issue - State: open - Opened by kasoushu about 1 month ago - 1 comment

#89 - How to implement the joint training?

Issue - State: open - Opened by eugenelyj about 1 month ago

#89 - How to implement the joint training?

Issue - State: open - Opened by eugenelyj about 1 month ago

#88 - How is the image prompts align with the text prompts

Issue - State: open - Opened by lxrswdd about 1 month ago

#88 - How is the image prompts align with the text prompts

Issue - State: open - Opened by lxrswdd about 1 month ago

#87 - priest

Issue - State: closed - Opened by QazalRezaee about 2 months ago

#87 - priest

Issue - State: closed - Opened by QazalRezaee about 2 months ago

#86 - Reason for downsampling in inference.py

Issue - State: open - Opened by daeunni about 2 months ago

#86 - Reason for downsampling in inference.py

Issue - State: open - Opened by daeunni about 2 months ago

#85 - Training/finetuning Code

Issue - State: open - Opened by cfeng16 about 2 months ago - 1 comment

#85 - Training/finetuning Code

Issue - State: open - Opened by cfeng16 about 2 months ago - 1 comment

#84 - Does it possible to replace the base model and DDIM schedule for faster and high quality video generation？

Issue - State: open - Opened by Young-Chin 2 months ago

#84 - Does it possible to replace the base model and DDIM schedule for faster and high quality video generation？

Issue - State: open - Opened by Young-Chin 2 months ago

#83 - Fix download stats on Hugging Face, improve discoverability

Issue - State: open - Opened by NielsRogge 2 months ago - 2 comments

#83 - Fix download stats on Hugging Face, improve discoverability

Issue - State: open - Opened by NielsRogge 2 months ago - 2 comments

#82 - convert image to video gpu consuming

Issue - State: open - Opened by esmaei1 3 months ago

#82 - convert image to video gpu consuming

Issue - State: open - Opened by esmaei1 3 months ago

#81 - Dose detailed caption improve the performance?

Issue - State: open - Opened by g-jing 3 months ago

#81 - Dose detailed caption improve the performance?

Issue - State: open - Opened by g-jing 3 months ago

#80 - cpu insted of gpu

Issue - State: open - Opened by esmaei1 3 months ago - 1 comment

#80 - cpu insted of gpu

Issue - State: open - Opened by esmaei1 3 months ago - 1 comment

#79 - different image input

Issue - State: open - Opened by esmaei1 3 months ago

#79 - different image input

Issue - State: open - Opened by esmaei1 3 months ago

#78 - CUDA out of memory

Issue - State: open - Opened by esmaei1 3 months ago - 1 comment

#78 - CUDA out of memory

Issue - State: open - Opened by esmaei1 3 months ago - 1 comment

#77 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: closed - Opened by jutochoppa 3 months ago - 3 comments

#77 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: closed - Opened by jutochoppa 3 months ago - 3 comments

#76 - Checkpoint folder

Issue - State: open - Opened by KintCark 4 months ago

#76 - Checkpoint folder

Issue - State: open - Opened by KintCark 4 months ago

#75 - Is any plan to make this work on Mac M1/M2/M3?

Issue - State: open - Opened by scottonly2 4 months ago

#75 - Is any plan to make this work on Mac M1/M2/M3?

Issue - State: open - Opened by scottonly2 4 months ago

#74 - How should I set up a "run_text2video Bash" file to obtain the output described in the videocrafter2 paper?

Issue - State: open - Opened by HangyeolLee12 5 months ago

#74 - How should I set up a "run_text2video Bash" file to obtain the output described in the videocrafter2 paper?

Issue - State: open - Opened by HangyeolLee12 5 months ago

#73 - Discord server flooded with spam!

Issue - State: open - Opened by LockMan007 6 months ago - 1 comment

#73 - Discord server flooded with spam!

Issue - State: open - Opened by LockMan007 6 months ago - 1 comment

#72 - better logging in inference.py 😁

Pull Request - State: open - Opened by hamza-m-farooqi 6 months ago

#72 - better logging in inference.py 😁

Pull Request - State: open - Opened by hamza-m-farooqi 6 months ago

#71 - 咨询有关 Text-Aligned Rich Image Embedding的技术细节

Issue - State: open - Opened by pokameng 6 months ago

#71 - 咨询有关 Text-Aligned Rich Image Embedding的技术细节

Issue - State: open - Opened by pokameng 6 months ago

#70 - How to use multiple gpus?

Issue - State: open - Opened by SYZhang0805 6 months ago

#70 - How to use multiple gpus?

Issue - State: open - Opened by SYZhang0805 6 months ago

#69 - How to perturb the temporal modules with only image datasets? (The implemenataion details in VideoCraft2)

Issue - State: open - Opened by Sora-Lite 7 months ago

#69 - How to perturb the temporal modules with only image datasets? (The implemenataion details in VideoCraft2)

Issue - State: open - Opened by Sora-Lite 7 months ago

#68 - about downloading open_clip_pytorch_model.bin

Issue - State: open - Opened by leizhu1989 7 months ago - 2 comments

#68 - about downloading open_clip_pytorch_model.bin

Issue - State: open - Opened by leizhu1989 7 months ago - 2 comments

#67 - Most important thing: how to fine tune this model?

Issue - State: open - Opened by musznik 7 months ago

#67 - Most important thing: how to fine tune this model?

Issue - State: open - Opened by musznik 7 months ago

#66 - how to select specific CUDA

Issue - State: open - Opened by xzitlou 7 months ago - 1 comment

#66 - how to select specific CUDA

Issue - State: open - Opened by xzitlou 7 months ago - 1 comment

#65 - Training hyper-parameters?

Issue - State: open - Opened by prismformore 7 months ago

#65 - Training hyper-parameters?

Issue - State: open - Opened by prismformore 7 months ago

#64 - Error on result screen

Issue - State: open - Opened by kadirovzafar 8 months ago

#64 - Error on result screen

Issue - State: open - Opened by kadirovzafar 8 months ago

#63 - Is there any model about I2V?

Issue - State: open - Opened by howardgriffin 8 months ago - 1 comment

#63 - Is there any model about I2V?

Issue - State: open - Opened by howardgriffin 8 months ago - 1 comment

#62 - inference.py: error: unrecognized arguments:

Issue - State: open - Opened by ruoxuer 8 months ago - 2 comments

#62 - inference.py: error: unrecognized arguments:

Issue - State: open - Opened by ruoxuer 8 months ago - 2 comments

#61 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: open - Opened by ruoxuer 8 months ago - 4 comments

#61 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: open - Opened by ruoxuer 8 months ago - 4 comments

#60 - Longer videos then 1 second?

Issue - State: open - Opened by Hokyjack 8 months ago - 3 comments

#60 - Longer videos then 1 second?

Issue - State: open - Opened by Hokyjack 8 months ago - 3 comments

#59 - Video Crafter 2 , Models and checkpoints

Issue - State: open - Opened by MahdiMohseni0033 8 months ago - 2 comments

#59 - Video Crafter 2 , Models and checkpoints

Issue - State: open - Opened by MahdiMohseni0033 8 months ago - 2 comments

#58 - about VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Issue - State: open - Opened by zhanghongyong123456 8 months ago - 1 comment

#58 - about VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Issue - State: open - Opened by zhanghongyong123456 8 months ago - 1 comment

#57 - 256 t2v inference config?

Issue - State: open - Opened by 18445864529 8 months ago

#57 - 256 t2v inference config?

Issue - State: open - Opened by 18445864529 8 months ago

#56 - Any plans to release the training code?

Issue - State: open - Opened by rohit901 8 months ago

#56 - Any plans to release the training code?

Issue - State: open - Opened by rohit901 8 months ago

#55 - After following all steps still get huge missmatch in loading the checkpoint

Issue - State: open - Opened by Wonder1905 9 months ago - 2 comments

#55 - After following all steps still get huge missmatch in loading the checkpoint

Issue - State: open - Opened by Wonder1905 9 months ago - 2 comments

#54 - How to generate growth videos

Issue - State: open - Opened by suwei999 9 months ago - 4 comments

#54 - How to generate growth videos

Issue - State: open - Opened by suwei999 9 months ago - 4 comments

#53 - missing keys in checkpoint of base_512_v1

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

#53 - missing keys in checkpoint of base_512_v1

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

#52 - Is this an issue with my version？

Issue - State: open - Opened by outman000 9 months ago - 1 comment

#52 - Is this an issue with my version？

Issue - State: open - Opened by outman000 9 months ago - 1 comment

#51 - Generate Quality

Issue - State: open - Opened by yy-fisher 10 months ago

#51 - Generate Quality

Issue - State: open - Opened by yy-fisher 10 months ago

#50 - any plans for onnx directml?

Issue - State: open - Opened by Amin456789 10 months ago

#50 - any plans for onnx directml?

Issue - State: open - Opened by Amin456789 10 months ago

#49 - A Bug in codes

Issue - State: open - Opened by Du-Yao 11 months ago

#49 - A Bug in codes

Issue - State: open - Opened by Du-Yao 11 months ago

#48 - Gradio 4.1.2 version object attribute modification

Pull Request - State: open - Opened by linuxdevopscn 11 months ago

#48 - Gradio 4.1.2 version object attribute modification

Pull Request - State: open - Opened by linuxdevopscn 11 months ago

#47 - How to use with other NVIDIA GPU

Issue - State: open - Opened by koala819 11 months ago - 2 comments

#47 - How to use with other NVIDIA GPU

Issue - State: open - Opened by koala819 11 months ago - 2 comments

#46 - About the training details

Issue - State: open - Opened by JacobKong 11 months ago

#46 - About the training details

Issue - State: open - Opened by JacobKong 11 months ago

#45 - About training code

Issue - State: open - Opened by lovejing0306 11 months ago - 4 comments

#45 - About training code

Issue - State: open - Opened by lovejing0306 11 months ago - 4 comments

#44 - Update README.md

Pull Request - State: open - Opened by eltociear 11 months ago - 1 comment

#44 - Update README.md

Pull Request - State: open - Opened by eltociear 11 months ago - 1 comment

GitHub / AILab-CVC/VideoCrafter issues and pull requests