"git@developer.sourcefind.cn:OpenDAS/ollama.git" did not exist on "cbc40aa9967d27a58f87442018f2d889782d1980"
[WIP] Add UniDiffuser model and pipeline (#2963)
* Fix a bug of pano when not doing CFG (#3030) * Fix a bug of pano when not doing CFG * enhance code quality * apply formatting. --------- Co-authored-by:Sayak Paul <spsayakpaul@gmail.com> * Text2video zero refinements (#3070) * fix progress bar issue in pipeline_text_to_video_zero.py. Copy scheduler after first backward * fix tensor loading in test_text_to_video_zero.py * make style && make quality * Release: v0.15.0 * [Tests] Speed up panorama tests (#3067) * fix: norm group test for UNet3D. * chore: speed up the panorama tests (fast). * set default value of _test_inference_batch_single_identical. * fix: batch_sizes default value. * [Post release] v0.16.0dev (#3072) * Adds profiling flags, computes train metrics average. (#3053) * WIP controlnet training - bugfix --streaming - bugfix running report_to!='wandb' - adds memory profile before validation * Adds final logging statement. * Sets train epochs to 11. Looking at a longer ~16ep run, we see only good validation images after ~11ep: https://wandb.ai/andsteing/controlnet_fill50k/runs/3j2hx6n8 * Removes --logging_dir (it's not used). * Adds --profile flags. * Updates --output_dir=runs/fill-circle-{timestamp}. * Compute mean of `train_metrics`. Previously `train_metrics[-1]` was logged, resulting in very bumpy train metrics. * Improves logging a bit. - adds l2_grads gradient norm logging - adds steps_per_sec - sets walltime as x coordinate of train/step - logs controlnet_params config * Adds --ccache (doesn't really help though). * minor fix in controlnet flax example (#2986) * fix the error when push_to_hub but not log validation * contronet_from_pt & controlnet_revision * add intermediate checkpointing to the guide * Bugfix --profile_steps * Sets `RACKER_PROJECT_NAME='controlnet_fill50k'`. * Logs fractional epoch. * Adds relative `walltime` metric. * Adds `StepTraceAnnotation` and uses `global_step` insetad of `step`. * Applied `black`. * Streamlines commands in README a bit. * Removes `--ccache`. This makes only a very small difference (~1 min) with this model size, so removing the option introduced in cdb3cc. * Re-ran `black`. * Update examples/controlnet/README.md Co-authored-by:
Pedro Cuenca <pedro@huggingface.co> --------- Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * Add TensorRT SD/txt2img Community Pipeline to diffusers along with TensorRT utils (#2974) * Add SD/txt2img Community Pipeline to diffusers along with TensorRT utils Signed-off-by:
Asfiya Baig <asfiyab@nvidia.com> * update installation command Signed-off-by:
⚙ ️chore(transformer_2d) update function signature for encoder_hidden_states * Update pipeline_stable_diffusion_inpaint_legacy.py (#2903) * Update pipeline_stable_diffusion_inpaint_legacy.py * fix preprocessing of Pil images with adequate batch size * revert map * add tests * reformat * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * next try to fix the style * wth is this * Update testing_utils.py * Update testing_utils.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py * Update test_stable_diffusion_inpaint_legacy.py --------- Co-authored-by:root <fulong_ye@163.com> * controlnet training resize inputs to multiple of 8 (#3135) controlnet training center crop input images to multiple of 8 The pipeline code resizes inputs to multiples of 8. Not doing this resizing in the training script is causing the encoded image to have different height/width dimensions than the encoded conditioning image (which uses a separate encoder that's part of the controlnet model). We resize and center crop the inputs to make sure they're the same size (as well as all other images in the batch). We also check that the initial resolution is a multiple of 8. * adding custom diffusion training to diffusers examples (#3031) * diffusers==0.14.0 update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion update * custom diffusion * custom diffusion * custom diffusion * custom diffusion * custom diffusion * apply formatting and get rid of bare except. * refactor readme and other minor changes. * misc refactor. * fix: repo_id issue and loaders logging bug. * fix: save_model_card. * fix: save_model_card. * fix: save_model_card. * add: doc entry. * refactor doc,. * custom diffusion * custom diffusion * custom diffusion * apply style. * remove tralining whitespace. * fix: toctree entry. * remove unnecessary print. * custom diffusion * custom diffusion * custom diffusion test * custom diffusion xformer update * custom diffusion xformer update * custom diffusion xformer update --------- Co-authored-by:
Nupur Kumari <nupurkumari@Nupurs-MacBook-Pro.local> Co-authored-by:
Nupur Kumari <nupurkumari@nupurs-mbp.wifi.local.cmu.edu> * make style * Update custom_diffusion.mdx (#3165) Add missing newlines for rendering the links correctly * Added distillation for quantization example on textual inversion. (#2760) * Added distillation for quantization example on textual inversion. Signed-off-by:
Ye, Xinyu <xinyu.ye@intel.com> * refined readme and code style. Signed-off-by:
Suraj Patil <surajp815@gmail.com> * update * Finish * Apply suggestions from code review --------- Co-authored-by:
William Berman <WLBberman@gmail.com> * Allow return pt x4 (#3236) * Add all files * update * Allow fp16 attn for x4 upscaler (#3239) * Add all files * update * Make sure vae is memory efficient for PT 1 * make style * fix fast test (#3241) * Adds a document on token merging (#3208) * add document on token merging. * fix headline. * fix: headline. * add some samples for comparison. * [AudioLDM] Update docs to use updated ckpt (#3240) * [AudioLDM] Update docs to use updated ckpt * make style * Release: v0.16.0 * Post release for 0.16.0 (#3244) * Post release * fix more * [docs] only mention one stage (#3246) * [docs] only mention one stage * add blurb on auto accepting --------- Co-authored-by:
njindal <njindal@adobe.com> * [Stochastic Sampler][Slow Test]: Cuda test fixes (#3257) [Slow Test]: Cuda test fixes Co-authored-by:
multimodalart <joaopaulo.passos+multimodal@gmail.com> * fix typo in score sde pipeline (#3132) * Fix typo in textual inversion JAX training script (#3123) The pipeline is built as `pipe` but then used as `pipeline`. * AudioDiffusionPipeline - fix encode method after config changes (#3114) * config fixes * deprecate get_input_dims * Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline"" (#3265) Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline" (#3201)" This reverts commit 91a2a80e . * Fix community pipelines (#3266) * update notebook (#3259) Co-authored-by:
yiyixuxu <yixu@yis-macbook-pro.lan> * [docs] add notes for stateful model changes (#3252) * [docs] add notes for stateful model changes * Update docs/source/en/optimization/fp16.mdx Co-authored-by:
👽 qol improvements for LoRA. * better function name? * fix: LoRA weight loading with the new format. * address Patrick's comments. * Apply suggestions from code review Co-authored-by:Horace He <horacehe2007@yahoo.com> * Add Horace He as co-author. Co-authored-by:
yiyixuxu <yixu310@gmail,com> * [docs] Improve safetensors docstring (#3368) * clarify safetensor docstring * fix typo * apply feedback * add: a warning message when using xformers in a PT 2.0 env. (#3365) * add: a warning message when using xformers in a PT 2.0 env. * Apply suggestions from code review Co-authored-by:
🚲 * relax tol for sd 1.0 * relax tol for controlnet. * determinism to img var. * relax tol for img variation. * tolerance to i2i sd * make style * determinism to inpaint. * relax tolerance for inpaiting. * determinism for inpainting legacy * relax tolerance. * determinism to instruct pix2pix * determinism to model editing. * model editing tolerance. * panorama determinism * determinism to pix2pix zero. * determinism to sag. * sd 2. determinism * sd. tolerance * disallow tf32 matmul. * relax tolerance is all you need. * make style and determinism to sd 2 depth * relax tolerance for depth. * tolerance to diffedit. * tolerance to sd 2 inpaint. * up tolerance. * determinism in upscaling. * tolerance in upscaler. * more tolerance relaxation. * determinism to v pred. * up tol for v_pred * unclip determinism * determinism to unclip img2img * determinism to text to video. * determinism to last set of tests * up tol. * vq cumsum doesn't have a deterministic kernel * relax tol * relax tol * [docs] Add transformers to install (#3388) add transformers to install * [deepspeed] partial ZeRO-3 support (#3076) * [deepspeed] partial ZeRO-3 support * cleanup * improve deepspeed fixes * Improve * make style --------- Co-authored-by:⚔ benchmark reports done * Apply suggestions from code review Co-authored-by:yueyang.hyy <yueyang.hyy@alibaba-inc.com> * [From ckpt] Fix from_ckpt (#3466) * Correct from_ckpt * make style * Update full dreambooth script to work with IF (#3425) * Add IF dreambooth docs (#3470) * parameterize pass single args through tuple (#3477) * attend and excite tests disable determinism on the class level (#3478) * dreambooth docs torch.compile note (#3471) * dreambooth docs torch.compile note * Update examples/dreambooth/README.md Co-authored-by:
StAlKeR7779 <stalkek7779@yandex.ru> --------- Co-authored-by:
Chanran Kim <seriousran@gmail.com> * DataLoader respecting EXIF data in Training Images (#3465) * DataLoader will now bake in any transforms or image manipulations contained in the EXIF Images may have rotations stored in EXIF. Training using such images will cause those transforms to be ignored while training and thus produce unexpected results * Fixed the Dataloading EXIF issue in main DreamBooth training as well * Run make style (black & isort) * make style * feat: allow disk offload for diffuser models (#3285) * allow disk offload for diffuser models * sort import * add max_memory argument * Changed sample[0] to images[0] (#3304) A pipeline object stores the results in `images` not in `sample`. Current code blocks don't work. * Typo in tutorial (#3295) * Torch compile graph fix (#3286) * fix more * Fix more * fix more * Apply suggestions from code review * fix * make style * make fix-copies * fix * make sure torch compile * Clean * fix test * Postprocessing refactor img2img (#3268) * refactor img2img VaeImageProcessor.postprocess * remove copy from for init, run_safety_checker, decode_latents Co-authored-by:
🚲 * relax tol for sd 1.0 * relax tol for controlnet. * determinism to img var. * relax tol for img variation. * tolerance to i2i sd * make style * determinism to inpaint. * relax tolerance for inpaiting. * determinism for inpainting legacy * relax tolerance. * determinism to instruct pix2pix * determinism to model editing. * model editing tolerance. * panorama determinism * determinism to pix2pix zero. * determinism to sag. * sd 2. determinism * sd. tolerance * disallow tf32 matmul. * relax tolerance is all you need. * make style and determinism to sd 2 depth * relax tolerance for depth. * tolerance to diffedit. * tolerance to sd 2 inpaint. * up tolerance. * determinism in upscaling. * tolerance in upscaler. * more tolerance relaxation. * determinism to v pred. * up tol for v_pred * unclip determinism * determinism to unclip img2img * determinism to text to video. * determinism to last set of tests * up tol. * vq cumsum doesn't have a deterministic kernel * relax tol * relax tol * [docs] Add transformers to install (#3388) add transformers to install * [deepspeed] partial ZeRO-3 support (#3076) * [deepspeed] partial ZeRO-3 support * cleanup * improve deepspeed fixes * Improve * make style --------- Co-authored-by:⚔ benchmark reports done * Apply suggestions from code review Co-authored-by:Ilia Larchenko <41329713+IliaLarchenko@users.noreply.github.com> Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
Umar <55330742+mu94-csl@users.noreply.github.com> Co-authored-by:
Mylo <36931363+gitmylo@users.noreply.github.com> Co-authored-by:
Markus Pobitzer <markuspobitzer@gmail.com> Co-authored-by:
Cheng Lu <lucheng.lc15@gmail.com> Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> Co-authored-by:
Isamu Isozaki <isamu.website@gmail.com> Co-authored-by:
Cesar Aybar <csaybar@gmail.com> Co-authored-by:
Will Rice <will@spokestack.io> Co-authored-by:
Adrià Arrufat <1671644+arrufat@users.noreply.github.com> Co-authored-by:
Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com> Co-authored-by:
At-sushi <dkahw210@kyoto.zaq.ne.jp> Co-authored-by:
Lucca Zenóbio <luccazen@gmail.com> Co-authored-by:
Lysandre Debut <lysandre@huggingface.co> Co-authored-by:
Isotr0py <41363108+Isotr0py@users.noreply.github.com> Co-authored-by:
pdoane <pdoane2@gmail.com> Co-authored-by:
Rupert Menneer <71332436+rupertmenneer@users.noreply.github.com> Co-authored-by:
sudowind <wfpkueecs@163.com> Co-authored-by:
Takuma Mori <takuma104@gmail.com> Co-authored-by:
Stas Bekman <stas00@users.noreply.github.com> Co-authored-by:
Laureηt <laurentfainsin@protonmail.com> Co-authored-by:
Jongwoo Han <jongwooo.han@gmail.com> Co-authored-by:
asfiyab-nvidia <117682710+asfiyab-nvidia@users.noreply.github.com> Co-authored-by:
clarencechen <clarencechenct@gmail.com> Co-authored-by:
Laureηt <laurent@fainsin.bzh> Co-authored-by:
superlabs-dev <133080491+superlabs-dev@users.noreply.github.com> Co-authored-by:
Dev Aggarwal <devxpy@gmail.com> Co-authored-by:
Vimarsh Chaturvedi <vimarsh.c@gmail.com> Co-authored-by:
7eu7d7 <31194890+7eu7d7@users.noreply.github.com> Co-authored-by:
cmdr2 <shashank.shekhar.global@gmail.com> Co-authored-by:
wfng92 <43742196+wfng92@users.noreply.github.com> Co-authored-by:
Glaceon-Hyy <ffheyy0017@gmail.com> Co-authored-by:
Ernie Chu <51432514+ernestchu@users.noreply.github.com> Co-authored-by:
Andranik Movsisyan <48154088+19and99@users.noreply.github.com> Co-authored-by:
Andreas Steiner <andstein@google.com> Co-authored-by:
Joseph Coffland <github@joe.coffland.com> Co-authored-by:
Tommaso De Rossi <beats.by.morse@gmail.com> Co-authored-by:
Cristian Garcia <cgarcia.e88@gmail.com> Co-authored-by:
cmdr2 <secondary.cmdr2@gmail.com> Co-authored-by:
1lint <105617163+1lint@users.noreply.github.com> Co-authored-by:
Chanchana Sornsoontorn <off9955555@gmail.com> Co-authored-by:
hwuebben <wbben123@yahoo.de> Co-authored-by:
superhero-7 <57797766+superhero-7@users.noreply.github.com> Co-authored-by:
nupurkmr9 <nupurkmr9@gmail.com> Co-authored-by:
Mishig <mishig.davaadorj@coloradocollege.edu> Co-authored-by:
regisss <15324346+regisss@users.noreply.github.com> Co-authored-by:
Youssef Adarrab <104783077+youssefadr@users.noreply.github.com> Co-authored-by:
Chengrui Wang <80876977+crywang@users.noreply.github.com> Co-authored-by:
SkyTNT <SKYTNT@outlook.com> Co-authored-by:
Isaac <34376531+init-22@users.noreply.github.com> Co-authored-by:
Yuchen Fan <fyc0624@gmail.com> Co-authored-by:
Nipun Jindal <jindal.nipun@gmail.com> Co-authored-by:
apolinário <joaopaulo.passos@gmail.com> Co-authored-by:
Xie Zejian <xiezej@gmail.com> Co-authored-by:
Jair Trejo <jairtrejo@gmail.com> Co-authored-by:
Robert Dargavel Smith <teticio@gmail.com> Co-authored-by:
Joqsan <6027118+Joqsan@users.noreply.github.com> Co-authored-by:
NimenDavid <312648004@qq.com> Co-authored-by:
M. Tolga Cangöz <46008593+standardAI@users.noreply.github.com> Co-authored-by:
timegate <timegate@kaist.ac.kr> Co-authored-by:
Jason Kuan <jason9075@users.noreply.github.com> Co-authored-by:
w4ffl35 <w4ffl35@ml1.net> Co-authored-by:
Seongsu Park <tjdtnsu@gmail.com> Co-authored-by:
Ambrosiussen <paul@ambrosiussen.com> Co-authored-by:
Hari Krishna <37787894+hari10599@users.noreply.github.com> Co-authored-by:
takuoko <to78314910@gmail.com> Co-authored-by:
Birch-san <Birch-san@users.noreply.github.com>
Showing
Please register or sign in to comment