- 21 Feb, 2025 2 commits
-
-
hlky authored
* `device_map` in `load_model_dict_into_meta` * _LOW_CPU_MEM_USAGE_DEFAULT * fix is_peft_version is_bitsandbytes_version
-
Aryan authored
* update * make fix-copies * update * tests * update * update * add co-author Co-Authored-By:
Langdx <82783347+Langdx@users.noreply.github.com> * add co-author Co-Authored-By:
howe <howezhang2018@gmail.com> * update --------- Co-authored-by:
-
- 20 Feb, 2025 1 commit
-
-
Sayak Paul authored
* poc encode_prompt() tests * fix * updates. * fixes * fixes * updates * updates * updates * revert * updates * updates * updates * updates * remove SDXLOptionalComponentsTesterMixin. * remove tests that directly leveraged encode_prompt() in some way or the other. * fix imports. * remove _save_load * fixes * fixes * fixes * fixes
-
- 19 Feb, 2025 1 commit
-
-
Marc Sun authored
* first draft model loading refactor * revert name change * fix bnb * revert name * fix dduf * fix huanyan * style * Update src/diffusers/models/model_loading_utils.py Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * suggestions from reviews * Update src/diffusers/models/modeling_utils.py Co-authored-by:
YiYi Xu <yixu310@gmail.com> * remove safetensors check * fix default value * more fix from suggestions * revert logic for single file * style * typing + fix couple of issues * improve speed * Update src/diffusers/models/modeling_utils.py Co-authored-by:
Aryan <aryan@huggingface.co> * fp8 dtype * add tests * rename resolved_archive_file to resolved_model_file * format * map_location default cpu * add utility function * switch to smaller model + test inference * Apply suggestions from code review Co-authored-by:
-
- 15 Feb, 2025 1 commit
-
-
Yuxuan Zhang authored
* init * encode with glm * draft schedule * feat(scheduler): Add CogView scheduler implementation * feat(embeddings): add CogView 2D rotary positional embedding * 1 * Update pipeline_cogview4.py * fix the timestep init and sigma * update latent * draft patch(not work) * fix * [WIP][cogview4]: implement initial CogView4 pipeline Implement the basic CogView4 pipeline structure with the following changes: - Add CogView4 pipeline implementation - Implement DDIM scheduler for CogView4 - Add CogView3Plus transformer architecture - Update embedding models Current limitations: - CFG implementation uses padding for sequence length alignment - Need to verify transformer inference alignment with Megatron TODO: - Consider separate forward passes for condition/uncondition instead of padding approach * [WIP][cogview4][refactor]: Split condition/uncondition forward pass in CogView4 pipeline Split the forward pass for conditional and unconditional predictions in the CogView4 pipeline to match the original implementation. The noise prediction is now done separately for each case before combining them for guidance. However, the results still need improvement. This is a work in progress as the generated images are not yet matching expected quality. * use with -2 hidden state * remove text_projector * 1 * [WIP] Add tensor-reload to align input from transformer block * [WIP] for older glm * use with cogview4 transformers forward twice of u and uc * Update convert_cogview4_to_diffusers.py * remove this * use main example * change back * reset * setback * back * back 4 * Fix qkv conversion logic for CogView4 to Diffusers format * back5 * revert to sat to cogview4 version * update a new convert from megatron * [WIP][cogview4]: implement CogView4 attention processor Add CogView4AttnProcessor class for implementing scaled dot-product attention with rotary embeddings for the CogVideoX model. This processor concatenates encoder and hidden states, applies QKV projections and RoPE, but does not include spatial normalization. TODO: - Fix incorrect QKV projection weights - Resolve ~25% error in RoPE implementation compared to Megatron * [cogview4] implement CogView4 transformer block Implement CogView4 transformer block following the Megatron architecture: - Add multi-modulate and multi-gate mechanisms for adaptive layer normalization - Implement dual-stream attention with encoder-decoder structure - Add feed-forward network with GELU activation - Support rotary position embeddings for image tokens The implementation follows the original CogView4 architecture while adapting it to work within the diffusers framework. * with new attn * [bugfix] fix dimension mismatch in CogView4 attention * [cogview4][WIP]: update final normalization in CogView4 transformer Refactored the final normalization layer in CogView4 transformer to use separate layernorm and AdaLN operations instead of combined AdaLayerNormContinuous. This matches the original implementation but needs validation. Needs verification against reference implementation. * 1 * put back * Update transformer_cogview4.py * change time_shift * Update pipeline_cogview4.py * change timesteps * fix * change text_encoder_id * [cogview4][rope] align RoPE implementation with Megatron - Implement apply_rope method in attention processor to match Megatron's implementation - Update position embeddings to ensure compatibility with Megatron-style rotary embeddings - Ensure consistent rotary position encoding across attention layers This change improves compatibility with Megatron-based models and provides better alignment with the original implementation's positional encoding approach. * [cogview4][bugfix] apply silu activation to time embeddings in CogView4 Applied silu activation to time embeddings before splitting into conditional and unconditional parts in CogView4Transformer2DModel. This matches the original implementation and helps ensure correct time conditioning behavior. * [cogview4][chore] clean up pipeline code - Remove commented out code and debug statements - Remove unused retrieve_timesteps function - Clean up code formatting and documentation This commit focuses on code cleanup in the CogView4 pipeline implementation, removing unnecessary commented code and improving readability without changing functionality. * [cogview4][scheduler] Implement CogView4 scheduler and pipeline * now It work * add timestep * batch * change convert scipt * refactor pt. 1; make style * refactor pt. 2 * refactor pt. 3 * add tests * make fix-copies * update toctree.yml * use flow match scheduler instead of custom * remove scheduling_cogview.py * add tiktoken to test dependencies * Update src/diffusers/models/embeddings.py Co-authored-by:
三洋三洋 <1258009915@qq.com> Co-authored-by:
OleehyO <leehy0357@gmail.com> Co-authored-by:
-
- 12 Feb, 2025 1 commit
-
-
Thanh Le authored
* Update peft_utils.py * Update peft_utils.py * Update peft_utils.py --------- Co-authored-by:
-
- 11 Feb, 2025 2 commits
-
-
Le Zhuo authored
* Add support for lumina2 --------- Co-authored-by:
csuhan <hanjiaming@whu.edu.cn> Co-authored-by:
hlky <hlky@hlky.ac>
-
Shitao Xiao authored
* OmniGen model.py * update OmniGenTransformerModel * omnigen pipeline * omnigen pipeline * update omnigen_pipeline * test case for omnigen * update omnigenpipeline * update docs * update docs * offload_transformer * enable_transformer_block_cpu_offload * update docs * reformat * reformat * reformat * update docs * update docs * make style * make style * Update docs/source/en/api/models/omnigen_transformer.md Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/using-diffusers/omnigen.md Co-authored-by:
-
- 28 Jan, 2025 1 commit
-
-
Sayak Paul authored
* conditionally check if compute capability is met. * log info. * fix condition. * updates * updates * updates * updates
-
- 27 Jan, 2025 1 commit
-
-
Aryan authored
* start pyramid attention broadcast * add coauthor Co-Authored-By:
Xuanlei Zhao <43881818+oahzxl@users.noreply.github.com> * update * make style * update * make style * add docs * add tests * update * Update docs/source/en/api/pipelines/cogvideox.md Co-authored-by:
DN6 <dhruv.nair@gmail.com> * update * fix remove hook behaviour --------- Co-authored-by:
-
- 23 Jan, 2025 1 commit
-
-
kahmed10 authored
add onnxruntime-migraphx to import_utils.py Co-authored-by:
-
- 21 Jan, 2025 3 commits
-
-
Lucain authored
-
Fanli Lin authored
* initial comit * fix empty cache * fix one more * fix style * update device functions * update * update * Update src/diffusers/utils/testing_utils.py Co-authored-by:
-
Sayak Paul authored
change licensing to 2025 from 2024.
-
- 19 Jan, 2025 1 commit
-
-
Shenghai Yuan authored
* Update __init__.py * add consisid * update consisid * update consisid * make style * make_style * Update src/diffusers/pipelines/consisid/pipeline_consisid.py Co-authored-by:
-
- 15 Jan, 2025 1 commit
-
-
Sayak Paul authored
* feat: support loading loras into 4bit quantized models. * updates * update * remove weight check.
-
- 14 Jan, 2025 1 commit
-
-
Marc Sun authored
* load and save dduf archive * style * switch to zip uncompressed * updates * Update src/diffusers/pipelines/pipeline_utils.py Co-authored-by:
Lucain <lucain@huggingface.co> * check path corectly * Apply suggestions from code review Co-authored-by:
-
- 23 Dec, 2024 1 commit
-
-
Aryan authored
* bump min torchao version to 0.7.0 * update
-
- 19 Dec, 2024 1 commit
-
-
hlky authored
-
- 18 Dec, 2024 1 commit
-
-
Andrés Romero authored
* flux_control_inpaint - failing test_flux_different_prompts * removing test_flux_different_prompts? * fix style * fix from PR comments * fix style * reducing guidance_scale in demo * Update src/diffusers/pipelines/flux/pipeline_flux_control_inpaint.py Co-authored-by:
affromero <ubuntu@ip-172-31-17-146.ec2.internal> Co-authored-by:
-
- 17 Dec, 2024 1 commit
-
-
Dhruv Nair authored
* update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * Update src/diffusers/quantizers/gguf/utils.py Co-authored-by:
-
- 16 Dec, 2024 2 commits
-
-
Aryan authored
* torchao quantizer --------- Co-authored-by:
-
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:
-
- 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:
🎉 [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:
Junyu Chen <chenjydl2003@gmail.com> Co-authored-by:
chenjy2003 <70215701+chenjy2003@users.noreply.github.com> 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:
-
- 11 Dec, 2024 1 commit
-
-
hlky authored
* ControlNetUnion model
-
- 10 Dec, 2024 2 commits
-
-
Darshil Jariwala authored
* using sd inpaint pipeline and sdxl pag inpaint pipeline to add changes * using sd inpaint pipeline and sdxl pag inpaint pipeline to add changes * finished the call function * added auto pipeline * merging diffusers * ready to test * ready to test * added copied from and removed unnecessary tests * make style changes * doc changes * updating example doc string * style fix * init * adding imports * quality * Update src/diffusers/pipelines/pag/pipeline_pag_sd_inpaint.py * make * Update tests/pipelines/pag/test_pag_sd_inpaint.py * slice and size * slice --------- Co-authored-by:
Darshil Jariwala <darshiljariwala@Darshils-MacBook-Air.local> Co-authored-by:
Darshil Jariwala <jariwala.darshil2002@gmail.com> Co-authored-by:
-
Aryan authored
* update --------- Co-authored-by:
-
- 06 Dec, 2024 3 commits
-
-
Juan Acevedo authored
* update ptxla example --------- Co-authored-by:
Juan Acevedo <jfacevedo@google.com> Co-authored-by:
Pei Zhang <zpcore@gmail.com> Co-authored-by:
Pei Zhang <piz@google.com> Co-authored-by:
Pei Zhang <pei@Peis-MacBook-Pro.local> Co-authored-by:
-
zhangp365 authored
* fixed a dtype bfloat16 bug in torch_utils.py when generating 1024*1024 image with bfloat16 dtype, there is an exception: File "/opt/conda/lib/python3.10/site-packages/diffusers/utils/torch_utils.py", line 107, in fourier_filter x_freq = fftn(x, dim=(-2, -1)) RuntimeError: Unsupported dtype BFloat16 * remove whitespace in torch_utils.py * Update src/diffusers/utils/torch_utils.py * Update torch_utils.py --------- Co-authored-by: -
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:
-
- 03 Dec, 2024 2 commits
-
-
Benjamin Paine authored
* fix progress bar updates in SD 1.5 PAG Img2Img pipeline --------- Co-authored-by:
-
Lucain authored
-
- 23 Nov, 2024 1 commit
-
-
Aryan authored
* update --------- Co-authored-by:
-
- 22 Nov, 2024 1 commit
-
-
Fanli Lin authored
* enable on xpu * add 1 more * add one more * enable more * add 1 more * add more * enable 1 * enable more cases * enable * enable * update comment * one more * enable 1 * add more cases * enable xpu * add one more caswe * add more cases * add 1 * add more * add more cases * add case * enable * add more * add more * add more * enbale more * add more * update code * update test marker * add skip back * update comment * remove single files * remove * style * add * revert * reformat * update decorator * update * update * update * Update tests/pipelines/deepfloyd_if/test_if.py Co-authored-by:
-
- 20 Nov, 2024 1 commit
-
-
YiYi Xu authored
* fix
-
- 08 Nov, 2024 1 commit
-
-
SahilCarterr authored
fix shutil.copy
-
- 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:
-
- 31 Oct, 2024 1 commit
-
-
Sayak Paul authored
* add a marker for big gpu tests * update * trigger on PRs temporarily. * onnx * fix * total memory * fixes * reduce memory threshold. * bigger gpu * empty * g6e * Apply suggestions from code review * address comments. * fix * fix * fix * fix * fix * okay * further reduce. * updates * remove * updates * updates * updates * updates * fixes * fixes * updates. * fix * workflow fixes. --------- Co-authored-by:
-
- 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:
-
