Aller au contenu
WorkflowPrésentéExterne
Ouvrir la source

Brie's Wan InfiniteTalk Lazy AI2V — v1.1

Minor tweak to the default prompt and node connections.

Sourcecivitai.com/models/1990483
TâcheMultipleCapacitésImage en vidéo · Texte en vidéoFamilleWanVersionRelease 2266559 — Brie_Wan_Lazy_i2v_infintetalk_v003.jsonEstimé VRAMNot yet characterizedBClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Version
Brie_Wan_Lazy_i2v_infintetalk_v003.json
Source
Civitai
Mis à jour
18 oct. 2026

Description de la source

Versions 1.1

Minor tweak to the default prompt and node connections.

Previous defaults were complex and connected to silence respectively.

What you need

Model files
19.4 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Exigences

Modèles

7

Packs de nœuds

5

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • Use Brie's Wan InfiniteTalk Lazy AI2V workflow to make an animated video of a character speaking with emotions and gestures from one character image, a dialog clip from an audio or video file, and a prompt.

Entrées et sorties

  • The described video lasts for the length of the audio clip, and the prompt may be simple or complex.

Installation

  • Version v1.1 is published by Slipperygem and lists Wan Video 14B i2v 720p as its base model.

Dépendances

  • Named model files include clip_vision_h.safetensors, nsfw_wan_umt5-xxl_bf16.safetensors, TencentGameMate/chinese-wav2vec2-base, and Wan2_1_VAE_fp32.safetensors.

  • Other named model files are Wan2_1-InfiniteTalk_Single_Q8.gguf, wan2.1-i2v-14b-720p-Q8_0.gguf, and Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors.

  • Named ComfyUI node packs are comfyui_essentials, comfyui-image-saver, comfyui-kjnodes, comfyui-videohelpersuite, and ComfyUI-WanVideoWrapper.

Configuration

  • The listed ComfyUI layout places clip_vision_h.safetensors in models/clip_vision, Wan2_1_VAE_fp32.safetensors in models/vae, and Wan 2.1 I2V 14B GGUF and FP8 models in models/diffusion_models.

  • Version v1.1 tweaks the default prompt and node connections; its description says the earlier prompt was complex and the audio connection went to silence.

Précautions

  • Before using the workflow, check that the named model files and node packs are available in your ComfyUI setup.

    Suggestion · non vérifié

  • No license information is listed, so check the applicable terms before sharing or publishing videos.

    Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipalVersion 2266559
civitai.com/models/1990483

Vérifié 18 oct.

Extraits de sources

3 extraits
Note18 oct.civitai.com/models/1990483

Source context: 517 downloads · Type Workflows · Base model Wan Video 14B i2v 720p

Note7 aoûtcivitai.com/models/1990483

Source context: 466 downloads · Type Workflows · Base model Wan Video 14B i2v 720p

Note19 juil.civitai.com/models/1990483

Source context: 449 downloads · Type Workflows · Base model Wan Video 14B i2v 720p