Star5
0
代码
代码
Issues
Pull Requests
项目讨论
Wiki
分析
Star5
0
HHeliosZhao[codex review] fix all chinese comment to english
9c9e37cd创建于 6月15日历史提交
文件最后提交记录最后更新时间
bash_run_inference_metric.sh
SANA-1.5 && FSDP training code (#196) * 1. update README.md 2. update train code; pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> merge train.py train_fsdp together, test sucessful; 1. add data/toy_data for tar vae loading training; 2. train.py train_fsdp.py all test passed; 1. update wids metadata script; update train.py Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. add create wid meta data script; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. update for sana-1.5; 2. add FSDP scripts; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update ci train; 2. code update; 3. update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code clean; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> update for bash file inference metrics; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. use dcae-1.1 for sana-1.5 2. update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
bash_run_inference_metric_dpg.sh
initial code update; Signed-off-by: junsongc <cjs1020440147@icloud.com>
1 年前
bash_run_inference_metric_geneval.sh
SANA-1.5 && FSDP training code (#196) * 1. update README.md 2. update train code; pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> merge train.py train_fsdp together, test sucessful; 1. add data/toy_data for tar vae loading training; 2. train.py train_fsdp.py all test passed; 1. update wids metadata script; update train.py Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. add create wid meta data script; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. update for sana-1.5; 2. add FSDP scripts; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update ci train; 2. code update; 3. update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code clean; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> update for bash file inference metrics; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. use dcae-1.1 for sana-1.5 2. update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
bash_run_inference_metric_imagereward.sh
initial code update; Signed-off-by: junsongc <cjs1020440147@icloud.com>
1 年前
infer_metric_run_inference_metric.sh
SANA-1.5 && FSDP training code (#196) * 1. update README.md 2. update train code; pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> merge train.py train_fsdp together, test sucessful; 1. add data/toy_data for tar vae loading training; 2. train.py train_fsdp.py all test passed; 1. update wids metadata script; update train.py Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. add create wid meta data script; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. update for sana-1.5; 2. add FSDP scripts; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update ci train; 2. code update; 3. update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code clean; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> update for bash file inference metrics; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. use dcae-1.1 for sana-1.5 2. update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
infer_metric_run_inference_metric_geneval.sh
SANA-1.5 && FSDP training code (#196) * 1. update README.md 2. update train code; pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> merge train.py train_fsdp together, test sucessful; 1. add data/toy_data for tar vae loading training; 2. train.py train_fsdp.py all test passed; 1. update wids metadata script; update train.py Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. add create wid meta data script; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> 1. update for sana-1.5; 2. add FSDP scripts; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update ci train; 2. code update; 3. update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code clean; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> update for bash file inference metrics; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. use dcae-1.1 for sana-1.5 2. update train.sh Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
infer_run_inference.sh
Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) (#177) * Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) * 1. add scripts of controlnet; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add all we need for controlnet inference and run successful; * move samples txt file into one dir; update readme; * 1. add readme for controlnet; 2. update readme; * add 1.6B controlnet related model and config files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update readme && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update readme.md * 1. add all need for online controlnet demo; 2. run success; * little bug fixed; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code update && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com> * 1. add test controlnet in CI; 2. fix controlnet config bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add ref image for controlnet; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet readme; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet CI; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
infer_run_inference_geneval.sh
inference scaling update (#208) * inference scaling update * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update scripts for geneval generation * move inference scaling md into asset/docs/ Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix number typo Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Chengyue Wu <chengyuew@cpu-00062.cm.cluster> Co-authored-by: lawrence-cj <cjs1020440147@icloud.com>
1 年前
infer_run_inference_geneval_diffusers.sh
fix the sample num bug in inference. Signed-off-by: lawrence-cj <cjs1020440147@icloud.com>
1 年前
inference.py
docs: fix some typos (#383) * docs: fix some typos Signed-off-by: John E <jeis4wpi@outlook.com> * pre-commit; --------- Signed-off-by: John E <jeis4wpi@outlook.com> Co-authored-by: junsong <cjs1020440147@icloud.com>
3 个月前
inference_dpg.py
Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) (#177) * Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) * 1. add scripts of controlnet; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add all we need for controlnet inference and run successful; * move samples txt file into one dir; update readme; * 1. add readme for controlnet; 2. update readme; * add 1.6B controlnet related model and config files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update readme && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update readme.md * 1. add all need for online controlnet demo; 2. run success; * little bug fixed; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code update && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com> * 1. add test controlnet in CI; 2. fix controlnet config bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add ref image for controlnet; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet readme; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet CI; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
inference_geneval.py
[codex review] fix all chinese comment to english
3 个月前
inference_geneval_diffusers.py
LongSANA: support SANA-Video + [LongLive](https://github.com/NVlabs/LongLive) (#341) * longsana training and inference code release * [CI-Lint] Fix code style issues with pre-commit 51181934710b656bf0792c4133cd44c32f4040c0 * update convert script; * update pre-commit version; * ci update; * revoke keys and update related code; * 1. add train val txt samples files for longsana; 2. clean yaml file for better vis; * pre-commit; * 1. add some TODOs where path need to be updated; 2. change all Chinese into English; 3. remove unused commands and comments; (stop before diffusion/longsana/trainer/longsana_trainer.py) * update data path and longsana docs * change `asset/longsana` to `data/longsana`, since the ./asset is not in gitignore, but ./data is. * 1. add longsana CI training test; 2. remove some unsed code; 3. add max_iters to the config in training scripts; * strict loss print to 4 digits; * 1. keep cleaning unsed code; 2. add longsana CI inference test; 3. add diffusers pipeline in md; * update readme; Co-authored-by: Shuai <a18310626323@163.com> * update model zoo * remove all unsed functions; * update readme; Co-authored-by: LoveSy <shana@zju.edu.cn> Co-authored-by: Enze Xie <johnny_ez@163.com> * fix some TODOs * pre-commit; * pre-commit; * ci update; * fix bug; * fix bugs; * fix bug; --------- Co-authored-by: GitHub Action <action@github.com> Co-authored-by: junsong <cjs1020440147@icloud.com> Co-authored-by: Shuai <a18310626323@163.com> Co-authored-by: LoveSy <shana@zju.edu.cn> Co-authored-by: Enze Xie <johnny_ez@163.com>
9 个月前
inference_image_reward.py
Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) (#177) * Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) * 1. add scripts of controlnet; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add all we need for controlnet inference and run successful; * move samples txt file into one dir; update readme; * 1. add readme for controlnet; 2. update readme; * add 1.6B controlnet related model and config files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update readme && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update readme.md * 1. add all need for online controlnet demo; 2. run success; * little bug fixed; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * code update && pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. update controlnet readme; 2. pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com> * 1. add test controlnet in CI; 2. fix controlnet config bug; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add ref image for controlnet; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet readme; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update controlnet CI; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com>
1 年前
inference_sana_sprint.py
LongSANA: support SANA-Video + [LongLive](https://github.com/NVlabs/LongLive) (#341) * longsana training and inference code release * [CI-Lint] Fix code style issues with pre-commit 51181934710b656bf0792c4133cd44c32f4040c0 * update convert script; * update pre-commit version; * ci update; * revoke keys and update related code; * 1. add train val txt samples files for longsana; 2. clean yaml file for better vis; * pre-commit; * 1. add some TODOs where path need to be updated; 2. change all Chinese into English; 3. remove unused commands and comments; (stop before diffusion/longsana/trainer/longsana_trainer.py) * update data path and longsana docs * change `asset/longsana` to `data/longsana`, since the ./asset is not in gitignore, but ./data is. * 1. add longsana CI training test; 2. remove some unsed code; 3. add max_iters to the config in training scripts; * strict loss print to 4 digits; * 1. keep cleaning unsed code; 2. add longsana CI inference test; 3. add diffusers pipeline in md; * update readme; Co-authored-by: Shuai <a18310626323@163.com> * update model zoo * remove all unsed functions; * update readme; Co-authored-by: LoveSy <shana@zju.edu.cn> Co-authored-by: Enze Xie <johnny_ez@163.com> * fix some TODOs * pre-commit; * pre-commit; * ci update; * fix bug; * fix bugs; * fix bug; --------- Co-authored-by: GitHub Action <action@github.com> Co-authored-by: junsong <cjs1020440147@icloud.com> Co-authored-by: Shuai <a18310626323@163.com> Co-authored-by: LoveSy <shana@zju.edu.cn> Co-authored-by: Enze Xie <johnny_ez@163.com>
9 个月前
inference_sana_sprint_geneval.py
Merging SANA-Sprint release code (#198) * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add files for SANA-Sprint; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update all bash inference metrics scripts up to date; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md cite; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. add two sana-sprint config files; 2. add sana-sprint train sh; 3. add sana_sprint.md for sana-sprint; 4. update README.md Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. add sana_sprint_pipeline 2. update sana_sprint.md Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * delete unused files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update model_zoo.md and README.md for sana-sprint; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug in launching test train. Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix `flow shift` bug in SANA 1.6B config file Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug in SanaConfig; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * temp remove previous test case; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bug for dpg_bench metadata.json Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. change all `predict_v` arg to `predict_flow_v` for more specific definition; 2. delete `predict_trigflow_v` and predcit_v` arg for no use; * 1. add all 3d rope and sincos pos embed for later use; 2. update code for schedule; 3. fix bugs; * update config files; Co-authored-by: Enze Xie <johnny_ez@163.com> * 1. fix bugs; 2. support auto-downloading ckpt when training; 3. pre-commit; * change all vae in config from 1.0 version to 1.1 version * fix bugs and run successful; * add sana-sprint inference scripts; * update ci test; * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update ci test ckpt path; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update ci test ckpt path; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix bugs in inference. * fix bugs * fix bug for flow diffusion training; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update a more specific cuda-toolkit version; * 1. fix bug for dc-ae-sana-1.1; * change all vae in config from 1.0 version to 1.1 version during training; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * Revert "change all vae in config from 1.0 version to 1.1 version during training;" This reverts commit a96983b59d61d9fcad563ee377a26db2cf10644d. * fix nan bug when online encode vae feature; * update config files; * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. add performance and HF model path 2. update readmes; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix controlnet inference bugs; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update readme Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * fix HF path bug && pre-commit Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update model_zoo.md Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> Co-authored-by: Enze Xie <johnny_ez@163.com> Co-authored-by: scxue <xueshuchen17@mails.ucas.edu.cn>
1 年前
interface.py
support 4K images (#135) * update diffusers convert script for 2K, 4K models; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update README.md and model_zoo.md; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add 4096 config files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * 1. add 4096 aspect ratio; 2. pre-commit Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * add 4K sana ComfyUI related files; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * update comfyui.md Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> * pre-commit; Signed-off-by: lawrence-cj <cjs1020440147@icloud.com> --------- Signed-off-by: lawrence-cj <cjs1020440147@icloud.com>
1 年前
style.css
initial code update; Signed-off-by: junsongc <cjs1020440147@icloud.com>
1 年前
sync_docs.py
New online docs sys (#346) * New online doc system * update path;
9 个月前