- 02 Mar, 2025 1 commit
-
-
YiYi Xu authored
* Add wanx pipeline, model and example * wanx_merged_v1 * change WanX into Wan * fix i2v fp32 oom error Link: https://code.alibaba-inc.com/open_wanx2/diffusers/codereview/20607813 * support t2v load fp32 ckpt * add example * final merge v1 * Update autoencoder_kl_wan.py * up * update middle, test up_block * up up * one less nn.sequential * up more * up * more * [refactor] [wip] Wan transformer/pipeline (#10926) * update * update * refactor rope * refactor pipeline * make fix-copies * add transformer test * update * update * make style * update tests * tests * conversion script * conversion script * update * docs * remove unused code * fix _toctree.yml * update dtype * fix test * fix tests: scale * up * more * Apply suggestions from code review * Apply suggestions from code review * style * Update scripts/convert_wan_to_diffusers.py * update docs * fix --------- Co-authored-by:
Yitong Huang <huangyitong.hyt@alibaba-inc.com> Co-authored-by:
亚森 <wangjiayu.wjy@alibaba-inc.com> Co-authored-by:
Aryan <aryan@huggingface.co>
-
- 25 Feb, 2025 1 commit
-
-
Daniel Regado authored
* Initial implementation of Flux multi IP-Adapter * Update src/diffusers/pipelines/flux/pipeline_flux.py Co-authored-by:
hlky <hlky@hlky.ac> * Update src/diffusers/pipelines/flux/pipeline_flux.py Co-authored-by:
-
- 24 Feb, 2025 2 commits
-
-
Aryan authored
* update * update * update
-
Sayak Paul authored
correct qk norm list.
-
- 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:
YiYi Xu <yixu310@gmail.com> * apply suggestions from review * use diffusers apply_rotary_emb * update flow match scheduler to accept timesteps * fix comment * apply review sugestions * Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py Co-authored-by:
三洋三洋 <1258009915@qq.com> Co-authored-by:
OleehyO <leehy0357@gmail.com> Co-authored-by:
-
- 31 Jan, 2025 1 commit
-
-
Max Podkorytov authored
* fix enable memory efficient attention on ROCm while calling CK implementation * Update attention_processor.py refactor of picking a set element
-
- 24 Jan, 2025 1 commit
-
-
Leo Jiang authored
* NPU Adaption for Sanna --------- Co-authored-by:
J石页 <jiangshuo9@h-partners.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
- 16 Jan, 2025 2 commits
-
-
Juan Acevedo authored
* implementing flux on TPUs with ptxla * add xla flux attention class * run make style/quality * Update src/diffusers/models/attention_processor.py Co-authored-by:
Juan Acevedo <jfacevedo@google.com> Co-authored-by:
-
Junyu Chen authored
* autoencoder_dc tiling * add tiling and slicing support in SANA pipelines * create variables for padding length because the line becomes too long * add tiling and slicing support in pag SANA pipelines * revert changes to tile size * make style * add vae tiling test * fix SanaMultiscaleLinearAttention apply_quadratic_attention bf16 --------- Co-authored-by:
-
- 24 Dec, 2024 1 commit
-
-
Eliseu Silva authored
Make passing the IP Adapter mask to the attention mechanism optional if there is no need to apply it to a given IP Adapter.
-
- 21 Dec, 2024 1 commit
-
-
hlky authored
* Flux IP-Adapter * test cfg * make style * temp remove copied from * fix test * fix test * v2 * fix * make style * temp remove copied from * Apply suggestions from code review Co-authored-by:
-
- 20 Dec, 2024 1 commit
-
-
Daniel Regado authored
* Added support for single IPAdapter on SD3.5 pipeline --------- Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> 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 * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * Update src/diffusers/models/transformers/transformer_mochi.py Co-authored-by:
-
- 16 Dec, 2024 2 commits
-
-
Steven Liu authored
* attnprocessors * lora * make style * fix * fix * sana * typo
-
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 2 commits
-
-
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:
-
Canva authored
* Add support for XFormers in SD3 * sd3 xformers test * sd3 xformers quality * sd3 xformers update --------- Co-authored-by:
-
- 06 Dec, 2024 2 commits
-
-
Juan Acevedo authored
* update ptxla example --------- 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:
-
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:
-
- 05 Dec, 2024 1 commit
-
-
YiYi Xu authored
-
- 03 Dec, 2024 1 commit
-
-
Benjamin Paine authored
* fix progress bar updates in SD 1.5 PAG Img2Img pipeline --------- Co-authored-by:
-
- 18 Nov, 2024 1 commit
-
-
ちくわぶ authored
Add all AttnProcessor in `AttentionProcessor` type
-
- 09 Nov, 2024 1 commit
-
-
Eliseu Silva authored
* Feature IP Adapter Xformers Attention Processor: this fix error loading incorrect attention processor when setting Xformers attn after load ip adapter scale, issues: #8863 #8872
-
- 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:
Dhruv Nair <dhruv.nair@gmail.com> * Update src/diffusers/pipelines/mochi/pipeline_mochi.py Co-authored-by:
-
- 01 Nov, 2024 1 commit
-
-
Leo Jiang authored
* NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX * NPU implementation for FLUX --------- 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:
-
- 21 Oct, 2024 1 commit
-
-
YiYi Xu authored
* update some docs and tests! --------- Co-authored-by:
Aryan <contact.aryanvs@gmail.com> Co-authored-by:
apolinário <joaopaulo.passos@gmail.com>
-
- 14 Oct, 2024 1 commit
-
-
Yuxuan.Zhang authored
* merge 9588 * max_shard_size="5GB" for colab running * conversion script updates; modeling test; refactor transformer * make fix-copies * Update convert_cogview3_to_diffusers.py * initial pipeline draft * make style * fight bugs
🐛 🪳 * add example * add tests; refactor * make style * make fix-copies * add co-author YiYi Xu <yixu310@gmail.com> * remove files * add docs * add co-author Co-Authored-By:
-
- 23 Aug, 2024 2 commits
-
-
Sayak Paul authored
* start fusing flux. * test * finish fusion * fix-copues
-
zR authored
* draft of embedding --------- Co-authored-by:
-
- 21 Aug, 2024 1 commit
-
-
YiYi Xu authored
* refactor rotary embeds * adding jsmidt as co-author of this PR for https://github.com/huggingface/diffusers/pull/9133 --------- Co-authored-by:
Joseph Smidt <josephsmidt@gmail.com>
-
- 06 Aug, 2024 2 commits
-
-
Ahn Donghoon (안동훈 / suno) authored
add pag sd3 --------- Co-authored-by:
HyoungwonCho <jhw9811@korea.ac.kr> Co-authored-by:
crepejung00 <jaewoojung00@naver.com> Co-authored-by:
-
Sayak Paul authored
* add fusion support to pixart * add to auraflow. * add tests * apply review feedback. * add back args and kwargs * style
-
- 05 Aug, 2024 1 commit
-
-
Aryan authored
* copy hunyuandit pipeline * pag variant of hunyuan dit * add tests * update docs * make style * make fix-copies * Update src/diffusers/pipelines/pag/pag_utils.py * remove incorrect copied from * remove pag hunyuan attn procs to resolve conflicts * add pag attn procs again * new implementation for pag_utils * revert pag changes * add pag refactor back; update pixart sigma * update pixart pag tests * apply suggestions from review Co-Authored-By: yixu310@gmail.com * make style * update docs, fix tests * fix tests * fix test_components_function since list not accepted as valid __init__ param * apply patch to fix broken tests Co-Authored-By:
-
- 04 Aug, 2024 2 commits
-
-
Aryan authored
* apply qk norm in attention processors * revert attention processor * qk-norm in only attention proc 2.0 and fused variant
-
psychedelicious authored
`None` is valid for `get_attention_scores`, should be typed as such
-
- 01 Aug, 2024 1 commit
-
-
Sayak Paul authored
add flux! Signed-off-by:
Adrien <adrien@huggingface.co> Co-authored-by:
Adrien <adrien.69740@gmail.com> Co-authored-by:
Anatoly Belikov <abelikov@singularitynet.io> 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:
-
- 26 Jul, 2024 1 commit
-
-
Aryan authored
-
