- 23 Dec, 2024 2 commits
-
-
Aryan authored
* update * make style * update * update * update * make style * single file related changes * update * fix * update single file urls and docs * update * fix
-
Aryan authored
* rename blocks and docs * fix docs --------- Co-authored-by:Dhruv Nair <dhruv.nair@gmail.com>
-
- 20 Dec, 2024 1 commit
-
-
Aryan authored
contiguous tensors in resnet Co-authored-by:YiYi Xu <yixu310@gmail.com>
-
- 19 Dec, 2024 1 commit
-
-
Aryan authored
* update * udpate * fix test
-
- 16 Dec, 2024 1 commit
-
-
Aryan authored
* copy transformer * copy vae * copy pipeline * make fix-copies * refactor; make original code work with diffusers; test latents for comparison generated with this commit * move rope into pipeline; remove flash attention; refactor * begin conversion script * make style * refactor attention * refactor * refactor final layer * their mlp -> our feedforward * make style * add docs * refactor layer names * refactor modulation * cleanup * refactor norms * refactor activations * refactor single blocks attention * refactor attention processor * make style * cleanup a bit * refactor double transformer block attention * update mochi attn proc * use diffusers attention implementation in all modules; checkpoint for all values matching original * remove helper functions in vae * refactor upsample * refactor causal conv * refactor resnet * refactor * refactor * refactor * grad checkpointing * autoencoder test * fix scaling factor * refactor clip * refactor llama text encoding * add coauthor Co-Authored-By:
"Gregory D. Hunkins" <greg@ollano.com> * refactor rope; diff: 0.14990234375; reason and fix: create rope grid on cpu and move to device Note: The following line diverges from original behaviour. We create the grid on the device, whereas original implementation creates it on CPU and then moves it to device. This results in numerical differences in layerwise debugging outputs, but visually it is the same. * use diffusers timesteps embedding; diff: 0.10205078125 * rename * convert * update * add tests for transformer * add pipeline tests; text encoder 2 is not optional * fix attention implementation for torch * add example * update docs * update docs * apply suggestions from review * refactor vae * update * Apply suggestions from code review Co-authored-by:
hlky <hlky@hlky.ac> * Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py Co-authored-by:
-
- 15 Dec, 2024 1 commit
-
-
Junsong Chen authored
[Sana] Add Sana, including `SanaPipeline`, `SanaPAGPipeline`, `LinearAttentionProcessor`, `Flow-based DPM-sovler` and so on. (#9982) * first add a script for DC-AE; * DC-AE init * replace triton with custom implementation * 1. rename file and remove un-used codes; * no longer rely on omegaconf and dataclass * replace custom activation with diffuers activation * remove dc_ae attention in attention_processor.py * iinherit from ModelMixin * inherit from ConfigMixin * dc-ae reduce to one file * update downsample and upsample * clean code * support DecoderOutput * remove get_same_padding and val2tuple * remove autocast and some assert * update ResBlock * remove contents within super().__init__ * Update src/diffusers/models/autoencoders/dc_ae.py Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> * add abstract * 1. add DCAE into diffusers; 2. make style and make quality; * add DCAE_HF into diffusers; * bug fixed; * add SanaPipeline, SanaTransformer2D into diffusers; * add sanaLinearAttnProcessor2_0; * first update for SanaTransformer; * first update for SanaPipeline; * first success run SanaPipeline; * model output finally match with original model with the same intput; * code update; * code update; * add a flow dpm-solver scripts *
🎉 [important update] 1. Integrate flow-dpm-sovler into diffusers; 2. finally run successfully on both `FlowMatchEulerDiscreteScheduler` and `FlowDPMSolverMultistepScheduler`; *🎉 🔧 [important update & fix huge bugs!!] 1. add SanaPAGPipeline & several related Sana linear attention operators; 2. `SanaTransformer2DModel` not supports multi-resolution input; 2. fix the multi-scale HW bugs in SanaPipeline and SanaPAGPipeline; 3. fix the flow-dpm-solver set_timestep() init `model_output` and `lower_order_nums` bugs; * remove prints; * add convert sana official checkpoint to diffusers format Safetensor. * Update src/diffusers/models/transformers/sana_transformer_2d.py Co-authored-by:Vinh H. Pham <phamvinh257@gmail.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * make the vae can be None in `__init__` of `SanaPipeline` * Update src/diffusers/models/transformers/sana_transformer_2d.py Co-authored-by:
Junyu Chen <chenjydl2003@gmail.com> Co-authored-by:
chenjy2003 <70215701+chenjy2003@users.noreply.github.com> Co-authored-by:
Aryan <aryan@huggingface.co> Co-authored-by:
-
- 12 Dec, 2024 1 commit
-
-
Aryan authored
* transformer * make style & make fix-copies * transformer * add transformer tests * 80% vae * make style * make fix-copies * fix * undo cogvideox changes * update * update * match vae * add docs * t2v pipeline working; scheduler needs to be checked * docs * add pipeline test * update * update * make fix-copies * Apply suggestions from code review Co-authored-by:
-
- 06 Dec, 2024 1 commit
-
-
Junsong Chen authored
* first add a script for DC-AE; * DC-AE init * replace triton with custom implementation * 1. rename file and remove un-used codes; * no longer rely on omegaconf and dataclass * replace custom activation with diffuers activation * remove dc_ae attention in attention_processor.py * iinherit from ModelMixin * inherit from ConfigMixin * dc-ae reduce to one file * update downsample and upsample * clean code * support DecoderOutput * remove get_same_padding and val2tuple * remove autocast and some assert * update ResBlock * remove contents within super().__init__ * Update src/diffusers/models/autoencoders/dc_ae.py Co-authored-by:
-
- 04 Dec, 2024 2 commits
-
-
Sayak Paul authored
* add: autoencoderkl tests * autoencodertiny. * fix * asymmetric autoencoder. * more * integration tests for stable audio decoder. * consistency decoder vae tests * remove grad check from consistency decoder. * cog * bye test_models_vae.py * fix * fix * remove allegro * fixes * fixes * fixes --------- Co-authored-by: -
Ivan Skorokhodov authored
Sometimes, the decoder might lack parameters and only buffers (e.g., this happens when we manually need to convert all the parameters to buffers — e.g. to avoid packing fp16 and fp32 parameters with FSDP)
-
- 03 Dec, 2024 1 commit
-
-
Emmanuel Benazera authored
* fix: missing AutoencoderKL lora adapter * fix --------- Co-authored-by:
-
- 29 Nov, 2024 1 commit
-
-
Sayak Paul authored
compute fourier features in FP32.
-
- 18 Nov, 2024 1 commit
-
-
Yuxuan.Zhang authored
* CogVideoX1_1PatchEmbed test * 1360 * 768 * refactor * make style * update docs * add modeling tests for cogvideox 1.5 * update * make fix-copies * add ofs embed(for convert) * add ofs embed(for convert) * more resolution for cogvideox1.5-5b-i2v * use even number of latent frames only * update pipeline implementations * make style * set patch_size_t as None by default * #skip frames 0 * refactor * make style * update docs * fix ofs_embed * update docs * invert_scale_latents * update * fix * Update docs/source/en/api/pipelines/cogvideox.md Co-authored-by:
-
- 08 Nov, 2024 1 commit
-
-
Michael Tkachuk authored
* refactored
-
- 05 Nov, 2024 1 commit
-
-
Aryan authored
* update * udpate * update transformer * make style * fix * add conversion script * update * fix * update * fix * update * fixes * make style * update * update * update * init * update * update * add * up * up * up * update * mochi transformer * remove original implementation * make style * update inits * update conversion script * docs * Update src/diffusers/pipelines/mochi/pipeline_mochi.py Co-authored-by:
-
- 30 Oct, 2024 1 commit
-
-
Aryan authored
fix
-
- 29 Oct, 2024 1 commit
-
-
Aryan authored
* update * refactor transformer part 1 * refactor part 2 * refactor part 3 * make style * refactor part 4; modeling tests * make style * refactor part 5 * refactor part 6 * gradient checkpointing * pipeline tests (broken atm) * update * add coauthor Co-Authored-By:
Huan Yang <hyang@fastmail.com> * refactor part 7 * add docs * make style * add coauthor Co-Authored-By:
-
- 16 Oct, 2024 1 commit
-
-
Aryan authored
* update * apply suggestions from review --------- Co-authored-by:
-
- 02 Oct, 2024 1 commit
-
-
Xiangchendong authored
Co-authored-by:
-
- 28 Sep, 2024 1 commit
-
-
Aryan authored
* remove conv cache from the layer and pass as arg instead * make style * yiyi's cleaner implementation Co-Authored-By:
-
- 26 Sep, 2024 1 commit
-
-
Aryan authored
* bugfix: precedence of operations should be slicing -> tiling * fix typo * fix another typo * deprecate current implementation of tiled_encode and use new impl * Update src/diffusers/models/autoencoders/autoencoder_kl.py Co-authored-by:
-
- 16 Sep, 2024 1 commit
-
-
Yuxuan.Zhang authored
* draft Init * draft * vae encode image * make style * image latents preparation * remove image encoder from conversion script * fix minor bugs * make pipeline work * make style * remove debug prints * fix imports * update example * make fix-copies * add fast tests * fix import * update vae * update docs * update image link * apply suggestions from review * apply suggestions from review * add slow test * make use of learned positional embeddings * apply suggestions from review * doc change * Update convert_cogvideox_to_diffusers.py * make style * final changes * make style * fix tests --------- Co-authored-by:
-
- 02 Sep, 2024 1 commit
-
-
Aryan authored
fake context parallel cache, vae encode tiling (cherry picked from commit bf890bca0e8aed875d6a207f9b826ce894901522)
-
- 23 Aug, 2024 1 commit
-
-
zR authored
* draft of embedding --------- Co-authored-by:
-
- 13 Aug, 2024 1 commit
-
-
Aryan authored
* refactor context parallel cache; update torch compile time benchmark * add tiling support * make style * remove num_frames % 8 == 0 requirement * update default num_frames to original value * add explanations + refactor * update torch compile example * update docs * update * clean up if-statements * address review comments * add test for vae tiling * update docs * update docs * update docstrings * add modeling test for cogvideox transformer * make style
-
- 07 Aug, 2024 1 commit
-
-
zR authored
* add CogVideoX --------- Co-authored-by:
Aryan <contact.aryanvs@gmail.com> Co-authored-by:
-
- 30 Jul, 2024 1 commit
-
-
Yoach Lacombe authored
* WIP modeling code and pipeline * add custom attention processor + custom activation + add to init * correct ProjectionModel forward * add stable audio to __initèè * add autoencoder and update pipeline and modeling code * add half Rope * add partial rotary v2 * add temporary modfis to scheduler * add EDM DPM Solver * remove TODOs * clean GLU * remove att.group_norm to attn processor * revert back src/diffusers/schedulers/scheduling_dpmsolver_multistep.py * refactor GLU -> SwiGLU * remove redundant args * add channel multiples in autoencoder docstrings * changes in docsrtings and copyright headers * clean pipeline * further cleaning * remove peft and lora and fromoriginalmodel * Delete src/diffusers/pipelines/stable_audio/diffusers.code-workspace * make style * dummy models * fix copied from * add fast oobleck tests * add brownian tree * oobleck autoencoder slow tests * remove TODO * fast stable audio pipeline tests * add slow tests * make style * add first version of docs * wrap is_torchsde_available to the scheduler * fix slow test * test with input waveform * add input waveform * remove some todos * create stableaudio gaussian projection + make style * add pipeline to toctree * fix copied from * make quality * refactor timestep_features->time_proj * refactor joint_attention_kwargs->cross_attention_kwargs * remove forward_chunk * move StableAudioDitModel to transformers folder * correct convert + remove partial rotary embed * apply suggestions from yiyixuxu -> removing attn.kv_heads * remove temb * remove cross_attention_kwargs * further removal of cross_attention_kwargs * remove text encoder autocast to fp16 * continue removing autocast * make style * refactor how text and audio are embedded * add paper * update example code * make style * unify projection model forward + fix device placement * make style * remove fuse qkv * apply suggestions from review * Update src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py Co-authored-by:
-
- 24 Jul, 2024 1 commit
-
-
Sayak Paul authored
* start debugging the problem, * start * fix * fix * fix imports. * handle hunyuan * remove residuals. * add a check for making sure there's appropriate procs. * add more rigor to the tests. * fix test * remove redundant check * fix-copies * move check_qkv_fusion_matches_attn_procs_length and check_qkv_fusion_processors_exist.
-
- 23 Jul, 2024 1 commit
-
-
Vishnu V Jaddipal authored
* Add attentionless VAE support * make style and quality, fix-copies --------- Co-authored-by:
-
- 11 Jul, 2024 1 commit
-
-
Dhruv Nair authored
update
-
- 27 Jun, 2024 1 commit
-
-
Sayak Paul authored
perform better deprecation for vqmodeloutput
-
- 21 Jun, 2024 1 commit
-
-
Sayak Paul authored
* get rid of the legacy lora remnants and make our codebase lighter * fix depcrecated lora argument * fix * empty commit to trigger ci * remove print * empty
-
- 18 Jun, 2024 1 commit
-
-
Sayak Paul authored
* shift factor argument to tiny * remove shift factor rejigging from the sd3 docs
-
- 12 Jun, 2024 1 commit
-
-
Dhruv Nair authored
* up * add sd3 * update * update * add tests * fix copies * fix docs * update * add dreambooth lora * add LoRA * update * update * update * update * import fix * update * Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py Co-authored-by:
-
- 04 Jun, 2024 1 commit
-
-
townwish4git authored
-
- 29 May, 2024 2 commits
-
-
Sayak Paul authored
move vqmodel to models.autoencoders.
-
Sayak Paul authored
* remove deprecated blocks. * update the location paths.
-
- 20 May, 2024 1 commit
-
-
Vinh H. Pham authored
make VAE compatible to torch.compile() Co-authored-by:
-
- 15 May, 2024 1 commit
-
-
Isamu Isozaki authored
* Init commit * Removed einops * Added default movq config for training * Update explanation of prompts * Fixed inheritance of discriminator and init_tracker * Fixed incompatible api between muse and here * Fixed output * Setup init training * Basic structure done * Removed attention for quick tests * Style fixes * Fixed vae/vqgan styles * Removed redefinition of wandb * Fixed log_validation and tqdm * Nothing commit * Added commit loss to lookup_from_codebook * Update src/diffusers/models/vq_model.py Co-authored-by:
-
- 10 May, 2024 1 commit
-
-
Mark Van Aken authored
* find & replace all FloatTensors to Tensor * apply formatting * Update torch.FloatTensor to torch.Tensor in the remaining files * formatting * Fix the rest of the places where FloatTensor is used as well as in documentation * formatting * Update new file from FloatTensor to Tensor
-
