From 22037243ab3ce923addda1229683b4ac5a66e00f Mon Sep 17 00:00:00 2001 From: kijai <40791699+kijai@users.noreply.github.com> Date: Tue, 11 Nov 2025 17:47:33 +0200 Subject: [PATCH 1/2] Fix Ovi audio negative prompt Had rather bad bug here which made Ovi audio always use the video negative prompt... --- Ovi/nodes_ovi.py | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/Ovi/nodes_ovi.py b/Ovi/nodes_ovi.py index aed883d..d71308f 100644 --- a/Ovi/nodes_ovi.py +++ b/Ovi/nodes_ovi.py @@ -8,6 +8,8 @@ from .vae.autoencoder import AutoEncoderModule from .vae.distributions import DiagonalGaussianDistribution import torchaudio +from ..utils import log + from comfy import model_management as mm device = mm.get_torch_device() offload_device = mm.unet_offload_device() @@ -216,9 +218,11 @@ class WanVideoOviCFG: def INPUT_TYPES(s): return {"required": { "original_text_embeds": ("WANVIDEOTEXTEMBEDS",), - "ovi_negative_text_embeds": ("WANVIDEOTEXTEMBEDS",), "ovi_audio_cfg": ("FLOAT", {"default": 3.0, "min": 0.0, "max": 100.0, "step": 0.01}), }, + "optional": { + "ovi_negative_text_embeds": ("WANVIDEOTEXTEMBEDS",), + } } RETURN_TYPES = ("WANVIDEOTEXTEMBEDS", ) @@ -227,10 +231,16 @@ class WanVideoOviCFG: CATEGORY = "WanVideoWrapper/Ovi" DESCRIPTION = "Adds Ovi negative text embeddings and audio CFG scale to the text embeddings dictionary" - def process(self, original_text_embeds, ovi_negative_text_embeds, ovi_audio_cfg): - negative_text_embeds = ovi_negative_text_embeds.get("negative_prompt_embeds", None) + def process(self, original_text_embeds, ovi_audio_cfg, ovi_negative_text_embeds=None): + negative_text_embeds = None + if ovi_negative_text_embeds is not None: + negative_text_embeds = ovi_negative_text_embeds.get("prompt_embeds", None) if negative_text_embeds is None: negative_text_embeds = original_text_embeds["prompt_embeds"] + log.info("WanVideoOviCFG: Ovi negative text embeddings not provided, using original prompt embeddings as negative embeddings") + else: + log.info("WanVideoOviCFG: Using provided Ovi audio negative text embeddings") + log.info("WanVideoOviCFG: negative text embedding shape: {}".format(negative_text_embeds[0].shape)) prompt_embeds_dict_copy = original_text_embeds.copy() prompt_embeds_dict_copy.update({ From ff26836cab68bfebc9da5cdce90967fb50bbca24 Mon Sep 17 00:00:00 2001 From: kijai <40791699+kijai@users.noreply.github.com> Date: Tue, 11 Nov 2025 18:53:11 +0200 Subject: [PATCH 2/2] Create wanvideo_2_2_5B_Ovi_image_to_video_audio_10_seconds_example_01.json --- ..._to_video_audio_10_seconds_example_01.json | 1507 +++++++++++++++++ 1 file changed, 1507 insertions(+) create mode 100644 example_workflows/wanvideo_2_2_5B_Ovi_image_to_video_audio_10_seconds_example_01.json diff --git a/example_workflows/wanvideo_2_2_5B_Ovi_image_to_video_audio_10_seconds_example_01.json b/example_workflows/wanvideo_2_2_5B_Ovi_image_to_video_audio_10_seconds_example_01.json new file mode 100644 index 0000000..505690f --- /dev/null +++ b/example_workflows/wanvideo_2_2_5B_Ovi_image_to_video_audio_10_seconds_example_01.json @@ -0,0 +1,1507 @@ +{ + "id": "7200c272-1c07-4834-9c36-c6ec5c140c21", + "revision": 0, + "last_node_id": 129, + "last_link_id": 213, + "nodes": [ + { + "id": 111, + "type": "WanVideoEncode", + "pos": [ + -489.00506591796875, + 735.4887084960938 + ], + "size": [ + 270, + 242 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 193 + }, + { + "name": "image", + "type": "IMAGE", + "link": 194 + }, + { + "name": "mask", + "shape": 7, + "type": "MASK", + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 195 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "de3c9c895a9b6730bfae10816ef955ed2b86b286", + "Node name for S&R": "WanVideoEncode" + }, + "widgets_values": [ + false, + 272, + 272, + 144, + 128, + 0, + 1 + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 91, + "type": "WanVideoTorchCompileSettings", + "pos": [ + -49.121726989746094, + 411.56317138671875 + ], + "size": [ + 342.74609375, + 250 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [ + 164 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "260c181e0ee11e0fcd1595c430c3c5357870e2c6", + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true, + 128, + false, + false + ], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 90, + "type": "WanVideoDecodeOviAudio", + "pos": [ + 2096.255126953125, + 378.9918212890625 + ], + "size": [ + 221.3249969482422, + 46 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "name": "mmaudio_vae", + "type": "MMAUDIOVAE", + "link": 161 + }, + { + "name": "samples", + "type": "LATENT", + "link": 162 + } + ], + "outputs": [ + { + "name": "audio", + "type": "AUDIO", + "links": [ + 163, + 190 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "260c181e0ee11e0fcd1595c430c3c5357870e2c6", + "Node name for S&R": "WanVideoDecodeOviAudio" + }, + "widgets_values": [] + }, + { + "id": 118, + "type": "WanVideoEasyCache", + "pos": [ + 1571.8782958984375, + 343.36279296875 + ], + "size": [ + 270, + 130 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "cache_args", + "type": "CACHEARGS", + "links": [] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "de3c9c895a9b6730bfae10816ef955ed2b86b286", + "Node name for S&R": "WanVideoEasyCache" + }, + "widgets_values": [ + 0.015, + 10, + -1, + "offload_device" + ] + }, + { + "id": 119, + "type": "MarkdownNote", + "pos": [ + 381.6411437988281, + 132.2297821044922 + ], + "size": [ + 435.8609313964844, + 151.15599060058594 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Model links", + "properties": {}, + "widgets_values": [ + "fp8_scaled:\n\n[https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/TI2V/Ovi](https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/TI2V/Ovi)\n\nbf16 and VAE:\n\n[https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Ovi](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Ovi)" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 108, + "type": "PreviewAudio", + "pos": [ + 2385.06689453125, + 195.56961059570312 + ], + "size": [ + 270, + 88 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 190 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 84, + "type": "WanVideoSetBlockSwap", + "pos": [ + 1239.550537109375, + 484.6754150390625 + ], + "size": [ + 202.5749969482422, + 46 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 152 + }, + { + "name": "block_swap_args", + "shape": 7, + "type": "BLOCKSWAPARGS", + "link": 154 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 153 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoSetBlockSwap" + }, + "widgets_values": [] + }, + { + "id": 127, + "type": "Note", + "pos": [ + -103.42256164550781, + 896.5643310546875 + ], + "size": [ + 210, + 120.13328552246094 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: T2V or I2V", + "properties": {}, + "widgets_values": [ + "For Text-to-video, disconnect the extra_latent input and manually set your width and height here" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 122, + "type": "Note", + "pos": [ + 1016.081298828125, + 594.9484252929688 + ], + "size": [ + 230, + 146 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: BF16 preferred", + "properties": {}, + "widgets_values": [ + "The original weights are only available in bf16, this model seem to have issues running in fp16 so if you get black output, make sure to use bf16 base_precision." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 126, + "type": "Note", + "pos": [ + 180.81106567382812, + 1191.43359375 + ], + "size": [ + 210, + 88 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: Audio latent", + "properties": {}, + "widgets_values": [ + "Default audio latent length is 157 for 121 frames, adjusting this is experimental!!" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 87, + "type": "WanVideoVAELoader", + "pos": [ + -442.4852600097656, + 254.36587524414062 + ], + "size": [ + 350.5255126953125, + 88.4420394897461 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "shape": 7, + "type": "WANCOMPILEARGS", + "link": null + } + ], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 159, + 193 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "1d940825636db49d5299e4f9634da6a8c36e26b8", + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "wanvideo\\Wan2_2_VAE_bf16.safetensors", + "bf16" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 125, + "type": "WanVideoEmptyMMAudioLatents", + "pos": [ + 187.17037963867188, + 1082.121337890625 + ], + "size": [ + 303.9961853027344, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 211 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "de3c9c895a9b6730bfae10816ef955ed2b86b286", + "Node name for S&R": "WanVideoEmptyMMAudioLatents" + }, + "widgets_values": [ + 314 + ] + }, + { + "id": 81, + "type": "WanVideoEmptyEmbeds", + "pos": [ + 173.6974334716797, + 899.3997802734375 + ], + "size": [ + 272.431640625, + 126 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "name": "control_embeds", + "shape": 7, + "type": "WANVIDIMAGE_EMBEDS", + "link": null + }, + { + "name": "extra_latents", + "shape": 7, + "type": "LATENT", + "link": 195 + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 198 + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 197 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 178 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoEmptyEmbeds" + }, + "widgets_values": [ + 992, + 512, + 241 + ] + }, + { + "id": 86, + "type": "WanVideoDecode", + "pos": [ + 2011.648007452393, + 582.8301297210694 + ], + "size": [ + 270, + 198 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 159 + }, + { + "name": "samples", + "type": "LATENT", + "link": 158 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 160 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "1d940825636db49d5299e4f9634da6a8c36e26b8", + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + false, + 272, + 272, + 144, + 128, + "default" + ], + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 109, + "type": "LoadImage", + "pos": [ + -627.6065673828125, + 1102.4898681640625 + ], + "size": [ + 274.07501220703125, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 192 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.3.68", + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "6 (4).png", + "image" + ] + }, + { + "id": 110, + "type": "ImageResizeKJv2", + "pos": [ + -288.9114685058594, + 1109.3226318359375 + ], + "size": [ + 270, + 336 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "name": "image", + "type": "IMAGE", + "link": 192 + }, + { + "name": "mask", + "shape": 7, + "type": "MASK", + "link": null + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 194 + ] + }, + { + "name": "width", + "type": "INT", + "links": [ + 198 + ] + }, + { + "name": "height", + "type": "INT", + "links": [ + 197 + ] + }, + { + "name": "mask", + "type": "MASK", + "links": null + } + ], + "properties": { + "cnr_id": "comfyui-kjnodes", + "ver": "c661baadd9683c0033cd2a6ad90157c6d099a6c2", + "Node name for S&R": "ImageResizeKJv2" + }, + "widgets_values": [ + 1280, + 720, + "lanczos", + "crop", + "0, 0, 0", + "center", + 32, + "cpu" + ] + }, + { + "id": 89, + "type": "OviMMAudioVAELoader", + "pos": [ + 1951.04345703125, + 192.66961669921875 + ], + "size": [ + 356.967529296875, + 106 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "mmaudio_vae", + "type": "MMAUDIOVAE", + "links": [ + 161 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "260c181e0ee11e0fcd1595c430c3c5357870e2c6", + "Node name for S&R": "OviMMAudioVAELoader" + }, + "widgets_values": [ + "mmaudio\\mmaudio_vae_16k_bf16.safetensors", + "mmaudio\\mmaudio_vocoder_bigvgan_best_netG_bf16.safetensors", + "bf16" + ], + "color": "#323", + "bgcolor": "#535" + }, + { + "id": 12, + "type": "WanVideoModelLoader", + "pos": [ + 384.0904235839844, + 437.55438232421875 + ], + "size": [ + 609.2658081054688, + 318 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "shape": 7, + "type": "WANCOMPILEARGS", + "link": 164 + }, + { + "name": "block_swap_args", + "shape": 7, + "type": "BLOCKSWAPARGS", + "link": null + }, + { + "name": "lora", + "shape": 7, + "type": "WANVIDLORA", + "link": null + }, + { + "name": "vram_management_args", + "shape": 7, + "type": "VRAM_MANAGEMENTARGS", + "link": null + }, + { + "name": "extra_model", + "shape": 7, + "type": "VACEPATH", + "link": null + }, + { + "name": "fantasytalking_model", + "shape": 7, + "type": "FANTASYTALKINGMODEL", + "link": null + }, + { + "name": "multitalk_model", + "shape": 7, + "type": "MULTITALKMODEL", + "link": null + }, + { + "name": "fantasyportrait_model", + "shape": 7, + "type": "FANTASYPORTRAITMODEL", + "link": null + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 152 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "37365817e82c3d6057fcb0a5d7f952f7376f096a", + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "WanVideo\\Ovi\\model_960x960_10s.safetensors", + "bf16", + "disabled", + "offload_device", + "sageattn", + "default" + ], + "color": "#223", + "bgcolor": "#335" + }, + { + "id": 83, + "type": "WanVideoBlockSwap", + "pos": [ + 845.3103637695312, + 129.08203125 + ], + "size": [ + 281.404296875, + 202 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 154 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 34, + false, + false, + true, + 0, + 1, + false + ] + }, + { + "id": 80, + "type": "WanVideoSampler", + "pos": [ + 1564.8895263671875, + 562.7935180664062 + ], + "size": [ + 327.80859375, + 873.2947265625 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 153 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 178 + }, + { + "name": "text_embeds", + "shape": 7, + "type": "WANVIDEOTEXTEMBEDS", + "link": 170 + }, + { + "name": "samples", + "shape": 7, + "type": "LATENT", + "link": 211 + }, + { + "name": "feta_args", + "shape": 7, + "type": "FETAARGS", + "link": null + }, + { + "name": "context_options", + "shape": 7, + "type": "WANVIDCONTEXT", + "link": null + }, + { + "name": "cache_args", + "shape": 7, + "type": "CACHEARGS", + "link": null + }, + { + "name": "flowedit_args", + "shape": 7, + "type": "FLOWEDITARGS", + "link": null + }, + { + "name": "slg_args", + "shape": 7, + "type": "SLGARGS", + "link": 191 + }, + { + "name": "loop_args", + "shape": 7, + "type": "LOOPARGS", + "link": null + }, + { + "name": "experimental_args", + "shape": 7, + "type": "EXPERIMENTALARGS", + "link": null + }, + { + "name": "sigmas", + "shape": 7, + "type": "SIGMAS", + "link": null + }, + { + "name": "unianimate_poses", + "shape": 7, + "type": "UNIANIMATE_POSE", + "link": null + }, + { + "name": "fantasytalking_embeds", + "shape": 7, + "type": "FANTASYTALKING_EMBEDS", + "link": null + }, + { + "name": "uni3c_embeds", + "shape": 7, + "type": "UNI3C_EMBEDS", + "link": null + }, + { + "name": "multitalk_embeds", + "shape": 7, + "type": "MULTITALK_EMBEDS", + "link": null + }, + { + "name": "freeinit_args", + "shape": 7, + "type": "FREEINITARGS", + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 158, + 162 + ] + }, + { + "name": "denoised_samples", + "type": "LATENT", + "links": null + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 50, + 4, + 5, + 45, + "fixed", + true, + "euler", + 0, + 1, + false, + "default", + 0, + -1, + false + ] + }, + { + "id": 85, + "type": "WanVideoTextEncodeCached", + "pos": [ + 412.3809509277344, + 1240.6162109375 + ], + "size": [ + 569.788818359375, + 595.4622192382812 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "extender_args", + "shape": 7, + "type": "WANVIDEOPROMPTEXTENDER_ARGS", + "link": null + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 167 + ] + }, + { + "name": "negative_text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": null + }, + { + "name": "positive_prompt", + "type": "STRING", + "links": null + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoTextEncodeCached" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "A large, brown, leather-clad automaton, holding a worn book, stands next to a small, blue, pig-shaped car in a dimly lit, rustic workshop. The automaton sighs and stretches, looking downwards. A small, orange-skinned character, wearing a pilot helmet adorned with colorful gadgets, pops up from the pig car, initially looking sleepy. The character lets out a big yawn, then slowly blinks awake, a smile spreading across its face. It then eagerly asks, Aren't we gonna test out my car in glorious ten second Ovi mode? Turning towards the automaton, it excitedly calls out, Hey, Gaga, check it out, we finally get enough time to hit second gear! As it gestures, beginning to say Isn't my piggy basically a cinematic universe now?, the automaton's hand abruptly drops the book. Audio: A soft sigh, a loud yawn, a high-pitched, enthusiastic child's voice, a sudden thud.", + "jitter, bad hands, blur, distortion", + "disabled", + false, + "gpu" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 93, + "type": "WanVideoSLG", + "pos": [ + 1102.8239013671875, + 905.1013565063474 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "slg_args", + "type": "SLGARGS", + "links": [ + 191 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "260c181e0ee11e0fcd1595c430c3c5357870e2c6", + "Node name for S&R": "WanVideoSLG" + }, + "widgets_values": [ + "11", + 0, + 1 + ] + }, + { + "id": 94, + "type": "WanVideoOviCFG", + "pos": [ + 1063.1351196289065, + 1069.2679473876954 + ], + "size": [ + 316.470703125, + 78 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "original_text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 167 + }, + { + "name": "ovi_negative_text_embeds", + "shape": 7, + "type": "WANVIDEOTEXTEMBEDS", + "link": 213 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 170 + ] + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "260c181e0ee11e0fcd1595c430c3c5357870e2c6", + "Node name for S&R": "WanVideoOviCFG" + }, + "widgets_values": [ + 3 + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 96, + "type": "WanVideoTextEncodeCached", + "pos": [ + 1022.1392211914062, + 1233.183837890625 + ], + "size": [ + 452.4334411621094, + 588.8506469726562 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "extender_args", + "shape": 7, + "type": "WANVIDEOPROMPTEXTENDER_ARGS", + "link": null + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [] + }, + { + "name": "negative_text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 213 + ] + }, + { + "name": "positive_prompt", + "type": "STRING", + "links": null + } + ], + "properties": { + "cnr_id": "ComfyUI-WanVideoWrapper", + "ver": "269a14f413ae1fcddfe54fc631688fc8ee032098", + "Node name for S&R": "WanVideoTextEncodeCached" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "", + "robotic, muffled, echo, distorted", + "disabled", + true, + "gpu" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 88, + "type": "VHS_VideoCombine", + "pos": [ + 2376.7099609375, + 387.7659912109375 + ], + "size": [ + 903.5481567382812, + 833.9514862060547 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 160 + }, + { + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 163 + }, + { + "name": "meta_batch", + "shape": 7, + "type": "VHS_BatchManager", + "link": null + }, + { + "name": "vae", + "shape": 7, + "type": "VAE", + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "cnr_id": "comfyui-videohelpersuite", + "ver": "0edce8ef7ce173ac97a3ed3d6f4636029d1a4530", + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 24, + "loop_count": 0, + "filename_prefix": "WanVideo_Ovi", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 20, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo_Ovi_00024-audio.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 24, + "workflow": "WanVideo_Ovi_00024.png", + "fullpath": "N:\\AI\\ComfyUI\\output\\WanVideo_Ovi_00024-audio.mp4" + } + } + } + }, + { + "id": 120, + "type": "Note", + "pos": [ + 530.448419189453, + 929.5005096435547 + ], + "size": [ + 369.08479725230814, + 177.81822065873598 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: Prompts", + "properties": {}, + "widgets_values": [ + "Ovi uses same positive prompt for both models, the tags and are MANDATORY and the spoken words should be inside them.\n\nFor the firstly released 720x720 5 seconds model, audio captions are between and . \n\nFor the newer models, audio captions come after the main prompt, starting with \"Audio:\"\n\nThe negative prompt can be different for each model." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 129, + "type": "Note", + "pos": [ + 1555.6138399436381, + 194.76287044872112 + ], + "size": [ + 299.7199999999998, + 88 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "EasyCache can be used to accelerate the generation, can affect video quality" + ], + "color": "#432", + "bgcolor": "#653" + } + ], + "links": [ + [ + 152, + 12, + 0, + 84, + 0, + "WANVIDEOMODEL" + ], + [ + 153, + 84, + 0, + 80, + 0, + "WANVIDEOMODEL" + ], + [ + 154, + 83, + 0, + 84, + 1, + "BLOCKSWAPARGS" + ], + [ + 158, + 80, + 0, + 86, + 1, + "LATENT" + ], + [ + 159, + 87, + 0, + 86, + 0, + "WANVAE" + ], + [ + 160, + 86, + 0, + 88, + 0, + "IMAGE" + ], + [ + 161, + 89, + 0, + 90, + 0, + "MMAUDIOVAE" + ], + [ + 162, + 80, + 0, + 90, + 1, + "LATENT" + ], + [ + 163, + 90, + 0, + 88, + 1, + "AUDIO" + ], + [ + 164, + 91, + 0, + 12, + 0, + "WANCOMPILEARGS" + ], + [ + 167, + 85, + 0, + 94, + 0, + "WANVIDEOTEXTEMBEDS" + ], + [ + 170, + 94, + 0, + 80, + 2, + "WANVIDEOTEXTEMBEDS" + ], + [ + 178, + 81, + 0, + 80, + 1, + "WANVIDIMAGE_EMBEDS" + ], + [ + 190, + 90, + 0, + 108, + 0, + "AUDIO" + ], + [ + 191, + 93, + 0, + 80, + 8, + "SLGARGS" + ], + [ + 192, + 109, + 0, + 110, + 0, + "IMAGE" + ], + [ + 193, + 87, + 0, + 111, + 0, + "WANVAE" + ], + [ + 194, + 110, + 0, + 111, + 1, + "IMAGE" + ], + [ + 195, + 111, + 0, + 81, + 1, + "LATENT" + ], + [ + 197, + 110, + 2, + 81, + 3, + "INT" + ], + [ + 198, + 110, + 1, + 81, + 2, + "INT" + ], + [ + 211, + 125, + 0, + 80, + 3, + "LATENT" + ], + [ + 213, + 96, + 1, + 94, + 1, + "WANVIDEOTEXTEMBEDS" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.6209213230591552, + "offset": [ + 1039.1538781007953, + 46.393301813241735 + ] + }, + "frontendVersion": "1.32.0", + "VHS_latentpreview": true, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "node_versions": { + "ComfyUI-WanVideoWrapper": "da43a516839b7bc50b21f53f1c4551862c872eac", + "ComfyUI-KJNodes": "3fcd22f2fe2be69c3229f192362b91888277cbcb", + "comfy-core": "0.3.64", + "comfyui-videohelpersuite": "8e4d79471bf1952154768e8435a9300077b534fa" + } + }, + "version": 0.4 +} \ No newline at end of file