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
• 1. diffusers support 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
• 1. 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 AutoencoderDC encode 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
• 1. diffusers support 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
• 1. 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 AutoencoderDC encode 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

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
• 1. diffusers support 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
• 1. 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 AutoencoderDC encode 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
• 1. diffusers support 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
• 1. 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 AutoencoderDC encode 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