Releases: NVlabs/Sana
Releases · NVlabs/Sana
Release list
SANA-Video && SANA-WM
What's Changed
- fix bugs and update inference examples; by @lawrence-cj in #217
- [fix bug] debug mode during training by @lawrence-cj in #220
- Adding svdquant required model type conversion script by @lawrence-cj in #222
- Fix args.image_size by @yujincheng08 in #223
- fix dead lock during training by @lawrence-cj in #224
- fix dataloader deadlock bug by @lawrence-cj in #225
- [ctrlnet] fix gradio by @yujincheng08 in #229
- Recovery inference CI test by @lawrence-cj in #230
- change gemma-2-2b-it path; by @lawrence-cj in #231
- add 0.6B Sana-Sprint model path by @lawrence-cj in #234
- code update; by @lawrence-cj in #237
- fix config path in README.md by @dotneet in #238
- fix bugs and update readme by @lawrence-cj in #245
- Fix a bug in FSDP checkpoint loading by @HeliosZhao in #247
- [fix] fix bugs in conversion to diffusers script by @lawrence-cj in #248
- Support SANA-1.5 in ComfyUI by @lawrence-cj in #249
- Refine gradio by @yujincheng08 in #262
- Nv labs GitHub repo by @lawrence-cj in #275
- fix diffusers model path in readme by @ashawkey in #263
- add reference code for sana-sprint by @lawrence-cj in #277
- Merge from ELM/main by @lawrence-cj in #281
- Update README.md to include ICCV acceptance by @sayakpaul in #292
- fix link in README.md by @sihyeong671 in #288
- Fixed Sana Sprint 0.6b config for train_scm_ladd by @CookedMorsel in #287
- Use js to select gallery by @yujincheng08 in #295
- support dc-ae-turbo by @chenjy2003 in #298
- Update DC-AE-Lite by @lawrence-cj in #299
- Sana Inpainting Feature by @Cedric-Perauer in #296
- Update README by @lawrence-cj in #305
- [SANA-Video] Adding SANA-Video Training & Inference code & Dataloader and so on by @lawrence-cj in #313
- add cover by @lawrence-cj in #315
- SANA-Video PR is under construction by @lawrence-cj in #321
- Support Image2Video inference; by @lawrence-cj in #324
- Upload SANA-Video Introduction Video by @lawrence-cj in #326
- add
SanaImageToVideoPipelineimage-to-video in diffusers pipeline by @lawrence-cj in #331 - Fixed checkpoint load & save bugs by @CookedMorsel in #334
- update readme; by @lawrence-cj in #336
- LongSANA: support SANA-Video + LongLive by @HeliosZhao in #341
- New online docs sys by @lawrence-cj in #346
- Fix docs bug by @lawrence-cj in #347
- Fix docs bug; by @lawrence-cj in #348
- fix minor docs bug; by @lawrence-cj in #349
- add image by @lawrence-cj in #350
- update readme; by @lawrence-cj in #351
- [feat] Add ltx vae refiner & SGLang support by @lawrence-cj in #361
- update sana-video 720p model and readme; by @lawrence-cj in #363
- Add Sol-RL post-training infrastructure by @lyttttt3333 in #368
- Add Sol-RL Post-Training Workflow by @lyttttt3333 in #369
- update readme; by @lawrence-cj in #370
- add SANA-WM in README. by @lawrence-cj in #374
- ci: enable fork PR testing + fix autolint label removal by @lawrence-cj in #382
- docs: fix some typos by @jeis4wpi in #383
- Release SANA-WM Streaming by @HaoyiZhu in #401
- Test HF-hosted Sana video asset link by @lawrence-cj in #402
New Contributors
- @dotneet made their first contribution in #238
- @HeliosZhao made their first contribution in #247
- @ashawkey made their first contribution in #263
- @sayakpaul made their first contribution in #292
- @sihyeong671 made their first contribution in #288
- @CookedMorsel made their first contribution in #287
- @chenjy2003 made their first contribution in #298
- @Cedric-Perauer made their first contribution in #296
- @jeis4wpi made their first contribution in #383
Full Changelog: v1.5.0...v2.0.0
Contributors
dotneet, yujincheng08, and 11 other contributors
Assets 2
SANA-1.5 && SANA-Sprint
What's Changed
- Inference with lower VRAM requirements by @frutiemax92 in #18
- Fix config loading for jupyter environments by @odusseys in #30
- Fix Dockerfile by @JimothyJohn in #34
- Relative import xformer triton depend fix by @lawrence-cj in #37
- remove triton dependency of DC-AE and fix bugs; by @lawrence-cj in #38
- Refine gradio by @yujincheng08 in #39
- fix the bug of stop training around 4 hours. by @lawrence-cj in #66
- add comfyui related files by @lawrence-cj in #77
- add a T2I2V video link into comfyui readme by @lawrence-cj in #78
-
diffuserssupport Sana; by @lawrence-cj in #88
- receive any kinds of image extension in
SanaImgDataset; by @lawrence-cj in #94 - add Sana-LoRA training and guidance by @lawrence-cj in #98
-
- update for 2Kpx models release; by @lawrence-cj in #103
- add config file for 2K models; by @lawrence-cj in #104
- update code for better quality by @lawrence-cj in #105
- fix the sample num bug in inference. by @lawrence-cj in #108
- Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #124
- fix the bug when resume rng_state with diffuerent gpu numbers. by @lawrence-cj in #131
- support 4K images by @lawrence-cj in #135
- [Tool]ImgDataset2WebDatasetMS by @Pevernow in #130
- fix 4K OOM with VAE-tiling by @lawrence-cj in #144
- docs: update README.md by @eltociear in #151
- fix: correct CSS property & missing articles by @CharlesCNorton in #152
- fix the bug for
AutoencoderDCencode training; by @lawrence-cj in #158 - Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #163
- update CI script; by @lawrence-cj in #165
- Sana1.5 8 bit CAME optimizer code release by @lawrence-cj in #167
- Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) by @lawrence-cj in #177
- update README by @lawrence-cj in #195
- SANA-1.5 && FSDP training code by @lawrence-cj in #196
- inference scaling update by @hills-code in #208
- Merging SANA-Sprint release code by @lawrence-cj in #198
- add a guidance to explore; by @lawrence-cj in #212
- update diffusers conversion script; by @lawrence-cj in #213
New Contributors
- @frutiemax92 made their first contribution in #18
- @odusseys made their first contribution in #30
- @JimothyJohn made their first contribution in #34
- @lawrence-cj made their first contribution in #37
- @yujincheng08 made their first contribution in #39
- @Pevernow made their first contribution in #130
- @eltociear made their first contribution in #151
- @CharlesCNorton made their first contribution in #152
- @hills-code made their first contribution in #208
Full Changelog: https://github.com/NVlabs/Sana/commits/v1.5.0
What's Changed
- Inference with lower VRAM requirements by @frutiemax92 in #18
- Fix config loading for jupyter environments by @odusseys in #30
- Fix Dockerfile by @JimothyJohn in #34
- Relative import xformer triton depend fix by @lawrence-cj in #37
- remove triton dependency of DC-AE and fix bugs; by @lawrence-cj in #38
- Refine gradio by @yujincheng08 in #39
- fix the bug of stop training around 4 hours. by @lawrence-cj in #66
- add comfyui related files by @lawrence-cj in #77
- add a T2I2V video link into comfyui readme by @lawrence-cj in #78
-
diffuserssupport Sana; by @lawrence-cj in #88
- receive any kinds of image extension in
SanaImgDataset; by @lawrence-cj in #94 - add Sana-LoRA training and guidance by @lawrence-cj in #98
-
- update for 2Kpx models release; by @lawrence-cj in #103
- add config file for 2K models; by @lawrence-cj in #104
- update code for better quality by @lawrence-cj in #105
- fix the sample num bug in inference. by @lawrence-cj in #108
- Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #124
- fix the bug when resume rng_state with diffuerent gpu numbers. by @lawrence-cj in #131
- support 4K images by @lawrence-cj in #135
- [Tool]ImgDataset2WebDatasetMS by @Pevernow in #130
- fix 4K OOM with VAE-tiling by @lawrence-cj in #144
- docs: update README.md by @eltociear in #151
- fix: correct CSS property & missing articles by @CharlesCNorton in #152
- fix the bug for
AutoencoderDCencode training; by @lawrence-cj in #158 - Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #163
- update CI script; by @lawrence-cj in #165
- Sana1.5 8 bit CAME optimizer code release by @lawrence-cj in #167
- Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) by @lawrence-cj in #177
- update README by @lawrence-cj in #195
New Contributors
- @frutiemax92 made their first contribution in #18
- @odusseys made their first contribution in #30
- @JimothyJohn made their first contribution in #34
- @yujincheng08 made their first contribution in #39
- @Pevernow made their first contribution in #130
- @eltociear made their first contribution in #151
- @CharlesCNorton made their first contribution in #152
Full Changelog: https://github.com/NVlabs/Sana/commits/v1.0.0
What's Changed
- SANA-1.5 && FSDP training code by @lawrence-cj in #196
- inference scaling update by @hills-code in #208
- Merging SANA-Sprint release code by @lawrence-cj in #198
- add a guidance to explore; by @lawrence-cj in #212
- update diffusers conversion script; by @lawrence-cj in #213
New Contributors
- @hills-code made their first contribution in #208
Full Changelog: v1.0.0...v1.5.0
Contributors
yujincheng08, odusseys, and 7 other contributors
Assets 2
SANA-1.0
What's Changed
- Inference with lower VRAM requirements by @frutiemax92 in #18
- Fix config loading for jupyter environments by @odusseys in #30
- Fix Dockerfile by @JimothyJohn in #34
- Relative import xformer triton depend fix by @lawrence-cj in #37
- remove triton dependency of DC-AE and fix bugs; by @lawrence-cj in #38
- Refine gradio by @yujincheng08 in #39
- fix the bug of stop training around 4 hours. by @lawrence-cj in #66
- add comfyui related files by @lawrence-cj in #77
- add a T2I2V video link into comfyui readme by @lawrence-cj in #78
-
diffuserssupport Sana; by @lawrence-cj in #88
- receive any kinds of image extension in
SanaImgDataset; by @lawrence-cj in #94 - add Sana-LoRA training and guidance by @lawrence-cj in #98
-
- update for 2Kpx models release; by @lawrence-cj in #103
- add config file for 2K models; by @lawrence-cj in #104
- update code for better quality by @lawrence-cj in #105
- fix the sample num bug in inference. by @lawrence-cj in #108
- Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #124
- fix the bug when resume rng_state with diffuerent gpu numbers. by @lawrence-cj in #131
- support 4K images by @lawrence-cj in #135
- [Tool]ImgDataset2WebDatasetMS by @Pevernow in #130
- fix 4K OOM with VAE-tiling by @lawrence-cj in #144
- docs: update README.md by @eltociear in #151
- fix: correct CSS property & missing articles by @CharlesCNorton in #152
- fix the bug for
AutoencoderDCencode training; by @lawrence-cj in #158 - Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #163
- update CI script; by @lawrence-cj in #165
- Sana1.5 8 bit CAME optimizer code release by @lawrence-cj in #167
- Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) by @lawrence-cj in #177
- update README by @lawrence-cj in #195
- SANA-1.5 && FSDP training code by @lawrence-cj in #196
- inference scaling update by @hills-code in #208
- Merging SANA-Sprint release code by @lawrence-cj in #198
- add a guidance to explore; by @lawrence-cj in #212
- update diffusers conversion script; by @lawrence-cj in #213
New Contributors
- @frutiemax92 made their first contribution in #18
- @odusseys made their first contribution in #30
- @JimothyJohn made their first contribution in #34
- @lawrence-cj made their first contribution in #37
- @yujincheng08 made their first contribution in #39
- @Pevernow made their first contribution in #130
- @eltociear made their first contribution in #151
- @CharlesCNorton made their first contribution in #152
- @hills-code made their first contribution in #208
Full Changelog: https://github.com/NVlabs/Sana/commits/v1.5.0
What's Changed
- Inference with lower VRAM requirements by @frutiemax92 in #18
- Fix config loading for jupyter environments by @odusseys in #30
- Fix Dockerfile by @JimothyJohn in #34
- Relative import xformer triton depend fix by @lawrence-cj in #37
- remove triton dependency of DC-AE and fix bugs; by @lawrence-cj in #38
- Refine gradio by @yujincheng08 in #39
- fix the bug of stop training around 4 hours. by @lawrence-cj in #66
- add comfyui related files by @lawrence-cj in #77
- add a T2I2V video link into comfyui readme by @lawrence-cj in #78
-
diffuserssupport Sana; by @lawrence-cj in #88
- receive any kinds of image extension in
SanaImgDataset; by @lawrence-cj in #94 - add Sana-LoRA training and guidance by @lawrence-cj in #98
-
- update for 2Kpx models release; by @lawrence-cj in #103
- add config file for 2K models; by @lawrence-cj in #104
- update code for better quality by @lawrence-cj in #105
- fix the sample num bug in inference. by @lawrence-cj in #108
- Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #124
- fix the bug when resume rng_state with diffuerent gpu numbers. by @lawrence-cj in #131
- support 4K images by @lawrence-cj in #135
- [Tool]ImgDataset2WebDatasetMS by @Pevernow in #130
- fix 4K OOM with VAE-tiling by @lawrence-cj in #144
- docs: update README.md by @eltociear in #151
- fix: correct CSS property & missing articles by @CharlesCNorton in #152
- fix the bug for
AutoencoderDCencode training; by @lawrence-cj in #158 - Nv labs GitHub repo/nv labs GitHub repo main by @lawrence-cj in #163
- update CI script; by @lawrence-cj in #165
- Sana1.5 8 bit CAME optimizer code release by @lawrence-cj in #167
- Nv labs GitHub repo/nv labs GitHub repo main adding controlnet (#23) by @lawrence-cj in #177
- update README by @lawrence-cj in #195
New Contributors
- @frutiemax92 made their first contribution in #18
- @odusseys made their first contribution in #30
- @JimothyJohn made their first contribution in #34
- @yujincheng08 made their first contribution in #39
- @Pevernow made their first contribution in #130
- @eltociear made their first contribution in #151
- @CharlesCNorton made their first contribution in #152
Full Changelog: https://github.com/NVlabs/Sana/commits/v1.0.0
Contributors
yujincheng08, odusseys, and 7 other contributors