open-mmlab/pia issues and pull requests

#54 - diffusion_pytorch_model.bin

Issue - State: closed - Opened by YujieOuO 4 months ago - 1 comment

#53 - bugifx: train.yaml trainable parameters

Pull Request - State: closed - Opened by zengyh1900 6 months ago

#52 - ERROR?

Issue - State: closed - Opened by Amo5 6 months ago

#51 - 作者好！我这边发现对于动漫类型的数据，很难保证生成的视频内容和输入图保持较高的一致性。我的实验内容如下：

Issue - State: closed - Opened by Amo5 6 months ago

#50 - [bugfix] support petreloss in dataset

Pull Request - State: closed - Opened by zengyh1900 7 months ago

#49 - RuntimeError: GET was unable to find an engine to execute this computation

Issue - State: closed - Opened by mamianshusheng 7 months ago - 2 comments

#48 - Upload missing gif files in README and remove petreloss in dependencies(pia.yml)

Pull Request - State: closed - Opened by ymzhang0319 7 months ago

#47 - models/mm_sd_v15_v2_full.ckpt

Issue - State: closed - Opened by yuminnko 7 months ago - 1 comment

#46 - 运行 demo 的时候报错

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

#45 - Many packages missing, till now i found this file missing as well "diffusion_pytorch_model.bin" please help

Issue - State: closed - Opened by Viper177 8 months ago - 3 comments

#44 - How long to train the model

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

#43 - [Feature] training scripts

Pull Request - State: closed - Opened by zengyh1900 8 months ago

#42 - about statistics in 'prepare_mask_coef_by_score'

Issue - State: closed - Opened by yuminnko 9 months ago - 6 comments

#41 - how to train?

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

#40 - different outputs with inference.py example

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

#39 - 缺少模型下载地址

Issue - State: closed - Opened by fallbernana123456 11 months ago - 1 comment

#38 - [Need-Community-Help] Add more sampling methods?

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

#37 - 视频时长问题

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

#36 - Update environment-pt2.yaml

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

#35 - Lighthouse demo doesn't seem to match teaser results.

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

#34 - Why not train conv_in.bias?

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

#33 - Add Replicate demo and API

Pull Request - State: closed - Opened by chenxwh about 1 year ago - 5 comments

#32 - About the weight and bias of Conv_in

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

#31 - [Update] Update readme

Pull Request - State: closed - Opened by LeoXing1996 about 1 year ago

#30 - xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.1.2+cu121 with CUDA 1201 (you have 2.1.2+cpu)

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

#29 - Can you provide a Windows model installation method?

Issue - State: closed - Opened by guahunyo about 1 year ago

#28 - Can you provide an extension to sdwebui or comfyui

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

#27 - cannot download pia.ckpt file vid gdown

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

#26 - [Feature] Support `scaled_dot_product_attention` in motion-module

Pull Request - State: closed - Opened by LeoXing1996 about 1 year ago

#25 - pia.ckpt gdown url miss?

Issue - State: closed - Opened by sunyuhan19981208 about 1 year ago - 2 comments

#24 - The generated face easily collapses.

Issue - State: open - Opened by sunyuhan19981208 about 1 year ago - 1 comment

#23 - Training code release

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

#22 - is this similar to LivePhoto?

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

#21 - Here is how to run this on Mac with Apple Silicon

Issue - State: open - Opened by YAY-3M-TA3 about 1 year ago - 4 comments

#20 - AMD gpu support?

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

#19 - Training Details

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

#18 - Can PIA checkpoint be used in A1111 webui?

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

#17 - Training code 😊

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

#17 - Training code 😊

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

#16 - Training code release？

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

#15 - training code

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

#14 - Training code release？

Issue - State: closed - Opened by JoshonSmith about 1 year ago

#13 - Unexpected key(s) in state_dict: "text_model.embeddings.position_ids".

Issue - State: open - Opened by anthonyyuan about 1 year ago - 5 comments

#12 - demo give error

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

#11 - [Fix] Update demo link in readme

Pull Request - State: closed - Opened by LeoXing1996 about 1 year ago

#10 - [Need-Community-Help] Training PIA for SDXL?

Issue - State: open - Opened by foureyednymph about 1 year ago - 3 comments
Labels: good first issue

#9 - License

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

#8 - Training code availability

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

#7 - Update video_transformer.py

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

#6 - [Fix] Fix download script url and change realistic vision version

Pull Request - State: closed - Opened by LeoXing1996 about 1 year ago

GitHub / open-mmlab/pia issues and pull requests