Hong Zhang ae8cb139e8 Support Torch Compile (#1368) ...

* support simple compile

* add support for compile

* minor fix

* minor fix

* minor fix

2026-03-24 11:19:43 +08:00

..

anima_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

dinov3_image_encoder.py

[NPU]:Replace 'cuda' in the project with abstract interfaces

2026-01-15 20:33:01 +08:00

flux2_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

flux2_text_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux2_vae.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_controlnet.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

flux_infiniteyou.py

flux series vram management

2025-07-15 20:11:02 +08:00

flux_ipadapter.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_lora_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_lora_patcher.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_text_encoder_clip.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_text_encoder_t5.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_vae.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

flux_value_control.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

general_modules.py

bugfix

2025-12-20 14:00:22 +08:00

longcat_video_dit.py

[NPU]:Replace 'cuda' in the project with abstract interfaces

2026-01-16 10:28:24 +08:00

ltx2_audio_vae.py

support ltx2.3 inference

2026-03-06 16:07:17 +08:00

ltx2_common.py

support ltx2.3 inference

2026-03-06 16:07:17 +08:00

ltx2_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

ltx2_text_encoder.py

ltx2.3 docs

2026-03-06 16:45:12 +08:00

ltx2_upsampler.py

add audio_vae, audio_vocoder, text_encoder, connector and upsampler for ltx2

2026-01-28 16:09:22 +08:00

ltx2_video_vae.py

ltx2.3 bugfix & ic lora (#1336)

2026-03-09 16:33:19 +08:00

model_loader.py

fix qwen_text_encoder bug in transformers>=5.2.0

2026-03-03 12:44:36 +08:00

mova_audio_dit.py

Mova (#1337)

2026-03-13 13:06:07 +08:00

mova_audio_vae.py

Mova (#1337)

2026-03-13 13:06:07 +08:00

mova_dual_tower_bridge.py

Mova (#1337)

2026-03-13 13:06:07 +08:00

nexus_gen_ar_model.py

[NPU]:Replace 'cuda' in the project with abstract interfaces

2026-01-15 20:33:01 +08:00

nexus_gen_projector.py

refine code

2025-07-29 20:02:34 +08:00

nexus_gen.py

refine code

2025-07-29 18:47:16 +08:00

qwen_image_controlnet.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

qwen_image_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

qwen_image_image2lora.py

support i2L

2025-12-09 22:07:35 +08:00

qwen_image_text_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

qwen_image_vae.py

support qwen-image-layered

2025-12-19 19:06:37 +08:00

sd_text_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

siglip2_image_encoder.py

[NPU]:Replace 'cuda' in the project with abstract interfaces

2026-01-15 20:33:01 +08:00

step1x_connector.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

step1x_text_encoder.py

[NPU]:Replace 'cuda' in the project with abstract interfaces

2026-01-15 20:33:01 +08:00

wan_video_animate_adapter.py

[feature]:Add adaptation of all models to zero3

2026-02-03 15:44:53 +08:00

wan_video_camera_controller.py

add wan2.2-fun-A14B inp, control and control-camera (#839)

2025-08-22 14:20:31 +08:00

wan_video_dit_s2v.py

[feature]:Add adaptation of all models to zero3

2026-01-31 16:50:18 +08:00

wan_video_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

wan_video_image_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

wan_video_mot.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

wan_video_motion_controller.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

wan_video_text_encoder.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

wan_video_vace.py

[feature]:Add adaptation of all models to zero3

2026-01-31 16:50:18 +08:00

wan_video_vae.py

Support WanToDance (#1361)

2026-03-20 16:40:35 +08:00

wantodance.py

Support WanToDance (#1361)

2026-03-20 16:40:35 +08:00

wav2vec.py

DiffSynth-Studio 2.0 major update

2025-12-04 16:33:07 +08:00

z_image_controlnet.py

support z-image controlnet

2026-01-07 15:56:53 +08:00

z_image_dit.py

Support Torch Compile (#1368)

2026-03-24 11:19:43 +08:00

z_image_image2lora.py

support z-image-omni-base-i2L

2026-01-07 20:36:53 +08:00

z_image_text_encoder.py

add research tutorial sec 1

2026-02-02 14:28:26 +08:00