wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-16 01:37:04 +08:00
Code Issues Actions 8 Packages Projects Releases Wiki Activity
943b3b615d
ComfyUI/comfy_extras
History
comfyanonymous 943b3b615d
HunyuanVideo 1.5 (#10819) 
* init

* update

* Update model.py

* Update model.py

* remove print

* Fix text encoding

* Prevent empty negative prompt

Really doesn't work otherwise

* fp16 works

* I2V

* Update model_base.py

* Update nodes_hunyuan.py

* Better latent rgb factors

* Use the correct sigclip output...

* Support HunyuanVideo1.5 SR model

* whitespaces...

* Proper latent channel count

* SR model fixes

This also still needs timesteps scheduling based on the noise scale, can be used with two samplers too already

* vae_refiner: roll the convolution through temporal

Work in progress.

Roll the convolution through time using 2-latent-frame chunks and a
FIFO queue for the convolution seams.

* Support HunyuanVideo15 latent resampler

* fix

* Some cleanup

Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>

* Proper hyvid15 I2V channels

Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>

* Fix TokenRefiner for fp16

Otherwise x.sum has infs, just in case only casting if input is fp16, I don't know if necessary.

* Bugfix for the HunyuanVideo15 SR model

* vae_refiner: roll the convolution through temporal II

Roll the convolution through time using 2-latent-frame chunks and a
FIFO queue for the convolution seams.

Added support for encoder, lowered to 1 latent frame to save more
VRAM, made work for Hunyuan Image 3.0 (as code shared).

Fixed names, cleaned up code.

* Allow any number of input frames in VAE.

* Better VAE encode mem estimation.

* Lowvram fix.

* Fix hunyuan image 2.1 refiner.

* Fix mistake.

* Name changes.

* Rename.

* Whitespace.

* Fix.

* Fix.

---------

Co-authored-by: kijai <40791699+kijai@users.noreply.github.com>
Co-authored-by: Rattus <rattus128@gmail.com>
2025-11-20 22:44:43 -05:00
..
chainner_models Replace print with logging (#6138) 2024-12-20 16:24:55 -05:00
nodes_ace.py v3 nodes (part a) (#9149) 2025-08-21 22:05:36 -04:00
nodes_advanced_samplers.py v3 nodes (part a) (#9149) 2025-08-21 22:05:36 -04:00
nodes_align_your_steps.py convert AlignYourStepsScheduler node to V3 schema (#9226) 2025-09-03 21:21:38 -04:00
nodes_apg.py v3 nodes (part a) (#9149) 2025-08-21 22:05:36 -04:00
nodes_attention_multiply.py v3 nodes (part a) (#9149) 2025-08-21 22:05:36 -04:00
nodes_audio_encoder.py convert nodes_audio_encoder.py to V3 schema (#10123) 2025-09-30 23:00:22 -07:00
nodes_audio.py Fix save audio nodes saving mono audio as stereo. (#10289) 2025-10-10 17:33:51 -04:00
nodes_camera_trajectory.py convert WanCameraEmbedding node to V3 schema (#9714) 2025-09-12 17:38:12 -04:00
nodes_canny.py convert Canny node to V3 schema (#9743) 2025-09-12 17:40:34 -04:00
nodes_cfg.py convert CFG nodes to V3 schema (#9717) 2025-09-12 17:39:55 -04:00
nodes_chroma_radiance.py Add support for Chroma Radiance (#9682) 2025-09-13 17:58:43 -04:00
nodes_clip_sdxl.py convert CLIPTextEncodeSDXL nodes to V3 schema (#9716) 2025-09-26 14:15:44 -07:00
nodes_compositing.py convert nodes_compositing.py to V3 schema (#10174) 2025-10-08 23:13:15 -07:00
nodes_cond.py convert nodes_cond.py to V3 schema (#9719) 2025-09-12 17:39:30 -04:00
nodes_context_windows.py Added context window support to core sampling code (#9238) 2025-08-13 21:33:05 -04:00
nodes_controlnet.py convert nodes_controlnet.py to V3 schema (#10202) 2025-10-17 14:13:05 -07:00
nodes_cosmos.py convert Cosmos nodes to V3 schema (#9721) 2025-09-12 17:38:46 -04:00
nodes_custom_sampler.py Add SamplingPercentToSigma node (#8963) 2025-07-19 23:09:11 -04:00
nodes_differential_diffusion.py convert nodes_differential_diffusion.py to V3 schema (#10056) 2025-10-01 12:17:33 -07:00
nodes_easycache.py EasyCache: Fix for mismatch in input/output channels with some models (#10788) 2025-11-18 07:00:21 -08:00
nodes_edit_model.py convert nodes_edit_model.py to V3 schema (#10147) 2025-10-03 13:24:42 -07:00
nodes_eps.py Add TemporalScoreRescaling node (#10351) 2025-10-15 18:12:25 -04:00
nodes_flux.py convert nodes_flux to V3 schema (#10122) 2025-10-09 16:07:17 -07:00
nodes_freelunch.py Move PAG to model_patches/unet section. 2024-07-18 17:22:51 -04:00
nodes_fresca.py convert nodes_fresca.py to V3 schema (#9951) 2025-09-26 14:12:04 -07:00
nodes_gits.py convert nodes_gits.py to V3 schema (#9949) 2025-10-01 12:16:59 -07:00
nodes_hidream.py convert nodes_hidream.py to V3 schema (#9946) 2025-09-26 23:13:05 -07:00
nodes_hooks.py Hooks Part 2 - TransformerOptionsHook and AdditionalModelsHook (#6377) 2025-01-11 12:20:23 -05:00
nodes_hunyuan3d.py convert hunyuan3d.py to V3 schema (#10664) 2025-11-19 14:49:01 -08:00
nodes_hunyuan.py HunyuanVideo 1.5 (#10819) 2025-11-20 22:44:43 -05:00
nodes_hypernetwork.py convert nodes_hypernetwork.py to V3 schema (#10583) 2025-11-03 00:21:47 -08:00
nodes_hypertile.py convert nodes_hypertile.py to V3 schema (#10061) 2025-09-27 19:16:22 -07:00
nodes_images.py ImageScaleToMaxDimension node. (#9689) 2025-09-02 20:05:57 -04:00
nodes_ip2p.py convert nodes_ip2p.pt to V3 schema (#10097) 2025-10-01 12:20:30 -07:00
nodes_latent.py convert nodes_latent.py to V3 schema (#10160) 2025-10-08 23:14:00 -07:00
nodes_load_3d.py support upload 3d model to custom subfolder (#8597) 2025-07-01 20:43:48 -04:00
nodes_lora_extract.py convert nodes_lora_extract.py to V3 schema (#10182) 2025-10-08 23:11:45 -07:00
nodes_lotus.py convert nodes_lotus.py to V3 schema (#10057) 2025-09-27 19:11:36 -07:00
nodes_lt.py Temp fix for LTXV custom nodes. (#10251) 2025-10-07 19:55:23 -04:00
nodes_lumina2.py convert nodes_lumina2.py to V3 schema (#10058) 2025-09-27 19:12:51 -07:00
nodes_mahiro.py convert nodes_mahiro.py to V3 schema (#10070) 2025-09-29 12:35:51 -07:00
nodes_mask.py Make LatentCompositeMasked work with basic video latents. (#10023) 2025-09-25 17:20:13 -04:00
nodes_mochi.py convert nodes_mochi.py to V3 schema (#10069) 2025-09-29 12:03:35 -07:00
nodes_model_advanced.py Add cosmos_rflow option to ModelSamplingContinuousEDM node. (#8523) 2025-06-13 17:47:52 -04:00
nodes_model_downscale.py convert nodes_model_downscale.py to V3 schema (#10199) 2025-10-08 23:10:23 -07:00
nodes_model_merging_model_specific.py Qwen Image model merging node. (#9202) 2025-08-06 04:07:04 -04:00
nodes_model_merging.py Make clipsave work with more TE models. (#7908) 2025-05-02 05:15:32 -04:00
nodes_model_patch.py USO style reference. (#9677) 2025-09-02 15:36:22 -04:00
nodes_morphology.py convert nodes_morphology.py to V3 schema (#10159) 2025-10-02 13:53:00 -07:00
nodes_nop.py Native block swap custom nodes considered harmful. (#10783) 2025-11-18 00:26:44 -05:00
nodes_optimalsteps.py convert nodes_optimalsteps.py to V3 schema (#10074) 2025-10-01 12:18:04 -07:00
nodes_pag.py convert nodes_pag.py to V3 schema (#10080) 2025-10-01 12:18:49 -07:00
nodes_perpneg.py convert nodes_perpneg.py to V3 schema (#10081) 2025-09-29 12:05:28 -07:00
nodes_photomaker.py convert nodes_photomaker.py to V3 schema (#10017) 2025-09-27 02:36:43 -07:00
nodes_pixart.py convert nodes_pixart.py to V3 schema (#10019) 2025-09-27 02:34:32 -07:00
nodes_post_processing.py convert nodes_post_processing to V3 schema (#9491) 2025-09-26 14:14:42 -07:00
nodes_preview_any.py change display name of PreviewAny node to "Preview as Text" (#10796) 2025-11-19 01:25:28 -08:00
nodes_primitive.py convert Primitive nodes to V3 schema (#9372) 2025-08-30 23:21:58 -04:00
nodes_qwen.py convert nodes_qwen.py to V3 schema (#10049) 2025-09-27 12:25:35 -07:00
nodes_rebatch.py convert nodes_rebatch.py to V3 schema (#9945) 2025-09-26 14:10:49 -07:00
nodes_rope.py Add a ScaleROPE node. Currently only works on WAN models. (#10559) 2025-10-30 22:11:38 -04:00
nodes_sag.py convert nodes_sag.py to V3 schema (#9940) 2025-09-26 14:13:52 -07:00
nodes_sd3.py convert nodes_sd3.py and nodes_slg.py to V3 schema (#10162) 2025-10-09 15:18:23 -07:00
nodes_sdupscale.py convert nodes_sdupscale.py to V3 schema (#9943) 2025-09-26 14:12:38 -07:00
nodes_slg.py convert nodes_sd3.py and nodes_slg.py to V3 schema (#10162) 2025-10-09 15:18:23 -07:00
nodes_stable3d.py convert nodes_stable3d.py to V3 schema (#10204) 2025-10-04 12:33:48 -07:00
nodes_stable_cascade.py convert Stable Cascade nodes to V3 schema (#9373) 2025-08-30 23:19:21 -04:00
nodes_string.py convert String nodes to V3 schema (#9370) 2025-08-21 22:03:57 -04:00
nodes_tcfg.py convert nodes_tcfg.py to V3 schema (#9942) 2025-09-26 14:13:05 -07:00
nodes_tomesd.py convert nodes_tomesd.py to V3 schema (#10180) 2025-10-03 11:50:38 -07:00
nodes_torch_compile.py convert nodes_torch_compile.py to V3 schema (#10173) 2025-10-03 11:43:54 -07:00
nodes_train.py Fix LoRA Trainer bugs with FP8 models. (#9854) 2025-09-20 21:24:48 -04:00
nodes_upscale_model.py convert nodes_upscale_model.py to V3 schema (#10149) 2025-10-09 16:08:40 -07:00
nodes_video_model.py Temporal area composition. 2025-03-03 06:50:31 -05:00
nodes_video.py convert Video nodes to V3 schema (#9489) 2025-08-30 23:19:54 -04:00
nodes_wan.py Fix bug with WanAnimateToVideo. (#9990) 2025-09-22 17:34:33 -04:00
nodes_webcam.py Fix WebcamCapture IS_CHANGED signature (#8413) 2025-06-09 13:05:54 -04:00