u 78094bc8ec feat: Implemented image-to-video latents using noise interpolation technique ...

- Applied the noise interpolation method from the paper "Improving Image Fidelity in Image-to-Video Generation using Noise Interpolation" (https://arxiv.org/pdf/2403.02827.pdf) to achieve high source image fidelity in I2V generation.
- Integrated the technique into our pipeline to enhance source image information during early denoising steps, leading to improved video output quality.
- Referenced and adapted the approach from the implementation available at https://noise-rectification.github.io/.

2024-08-31 23:10:29 +08:00

..

chainner_models

Keep compatibility with some custom nodes.

2024-05-26 15:37:41 -04:00

nodes_advanced_samplers.py

Fix SamplerEulerCFGpp node.

2024-07-02 12:21:08 -04:00

nodes_align_your_steps.py

Add a denoise value to AlignYourStepsScheduler.

2024-04-27 00:48:41 -04:00

nodes_attention_multiply.py

Add some nodes to multiply the attention in UNet and Clip models.

2024-04-28 13:03:43 -04:00

nodes_audio.py

Add missing import (#4174)

2024-08-02 09:34:12 -04:00

nodes_canny.py

Remove some unused imports.

2024-05-27 19:08:27 -04:00

nodes_clip_sdxl.py

Don't make dynamicPrompts the default on multiline string inputs.

2024-04-13 16:18:00 -04:00

nodes_cogvidex_model.py

feat: Implemented image-to-video latents using noise interpolation technique

2024-08-31 23:10:29 +08:00

nodes_compositing.py

Fix alpha in PorterDuffImageComposite. (#3411)

2024-06-04 16:37:11 -04:00

nodes_cond.py

Don't make dynamicPrompts the default on multiline string inputs.

2024-04-13 16:18:00 -04:00

nodes_controlnet.py

"auto" type is only relevant to the SetUnionControlNetType node.

2024-07-22 11:30:38 -04:00

nodes_custom_sampler.py

Add dpmpp_2s_ancestral as custom sampler (#4101)

2024-07-27 16:19:50 -04:00

nodes_differential_diffusion.py

Fix differential diffusion node for batches.

2024-03-04 00:43:09 -05:00

nodes_flux.py

Add FluxGuidance node.

2024-08-02 10:25:49 -04:00

nodes_freelunch.py

Move PAG to model_patches/unet section.

2024-07-18 17:22:51 -04:00

nodes_gits.py

feat: add gits scheduler (#3769)

2024-06-20 08:12:15 -04:00

nodes_hunyuan.py

Cleanup HunyuanDit controlnets.

2024-08-09 02:59:34 -04:00

nodes_hypernetwork.py

Switch some more prints to logging.

2024-03-11 16:34:58 -04:00

nodes_hypertile.py

Move PAG to model_patches/unet section.

2024-07-18 17:22:51 -04:00

nodes_images.py

Increase image batch nodes maximum values.

2024-03-17 08:57:49 -04:00

nodes_ip2p.py

Add InstructPixToPixConditioning node.

2024-04-04 15:06:17 -04:00

nodes_latent.py

changed default of LatentBatchSeedBehavior to fixed

2024-02-02 18:31:35 +09:00

nodes_mask.py

Add a ThresholdMask node.

2024-03-04 00:31:59 -05:00

nodes_model_advanced.py

ModelSamplingFlux now takes a resolution and adjusts the shift with it.

2024-08-04 04:06:00 -04:00

nodes_model_downscale.py

Use get_model_object in Deep Shrink node (#3408)

2024-05-06 18:39:39 -04:00

nodes_model_merging_model_specific.py

Add advanced model merge node for Flux model.

2024-08-02 23:20:53 -04:00

nodes_model_merging.py

CheckpointSave node name.

2024-08-19 15:06:12 -04:00

nodes_morphology.py

Add Morphology nodes from kornia (#2781)

2024-03-04 12:50:28 -05:00

nodes_pag.py

Lower SAG scale step for finer control (#4158)

2024-08-02 10:29:03 -04:00

nodes_perpneg.py

Fix to allow use of PerpNegGuider with cfg_function_post hooks (like PAG) (#3618)

2024-06-01 12:36:08 -04:00

nodes_photomaker.py

Don't make dynamicPrompts the default on multiline string inputs.

2024-04-13 16:18:00 -04:00

nodes_post_processing.py

Speed up Sharpen node.

2024-04-21 09:02:06 -04:00

nodes_rebatch.py

Add a RebatchImages node.

2023-12-20 16:22:18 -05:00

nodes_sag.py

Lower SAG scale step for finer control (#4158)

2024-08-02 10:29:03 -04:00

nodes_sd3.py

Cleanup HunyuanDit controlnets.

2024-08-09 02:59:34 -04:00

nodes_sdupscale.py

Remove some unused imports.

2024-05-27 19:08:27 -04:00

nodes_stable3d.py

SV3D support.

2024-03-18 16:54:13 -04:00

nodes_stable_cascade.py

Fix stable cascade img2img not working with all resolutions.

2024-03-18 13:51:38 -04:00

nodes_tomesd.py

Add some more transformer hooks and move tomesd to comfy_extras.

2023-06-24 03:30:22 -04:00

nodes_upscale_model.py

Import spandrel_extra_arches if present.

2024-05-28 01:42:11 -04:00

nodes_video_model.py

SV3D support.

2024-03-18 16:54:13 -04:00

nodes_webcam.py

Add webcam node (#3497)

2024-05-17 13:16:08 -04:00