WorkflowListedExternal

MOTION-FORGE HuMo 17B — Speech-to-Video (Lip-Sync) — v1.0

A speech-to-video character animation workflow powered by HuMo-17B, turning a single still into a talking-head performance driven by uploaded audio. Audio is encoded with Whisper-large v3, merged with CLIP prompt...

Sourcecivitai.com/models/2037986

VersionRelease 2306605 — MOTION_FORGE_HUMO_17B_s2v.jsonEstimated VRAMNot yet characterizedDgrade

Runtime profile

Access: External workflow
Status: Listed
Version: MOTION_FORGE_HUMO_17B_s2v.json
Source: Civitai
Updated: Oct 17, 2026

Source description

No release description captured.

What you need

Model files: 4.5 GiB known subtotal

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

Requirements

Models

cow-umt5xxl-q8_0.gguf
Not resolved
Text encoder · Unknown
HuMo-17b-Q8_0.gguf
Not resolved
Checkpoint · Unknown
lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors
File specified
LoRA · 1.37 GB · Civitai · 1585622
pig_wan_vae_fp32-f16.gguf
File specified
VAE · 242 MB · Hugging Face · Kutches/Kr3a
whisper_large_v3_fp16.safetensors
File observed at source
Checkpoint · 2.88 GB · SAFETENSORS · Unknown

Node packs

comfyui-easy-use
Found
Node pack · Registry
comfyui-videohelpersuite
Found
Node pack · Registry
gguf
Found
Node pack · Registry

Sources

1 source

CivitaiPrimaryVersion 2306605

civitai.com/models/2037986

Verified Oct 17

Model artifacts

1 artifact

motionFORGEHumo17BSpeech_v10.zip

zip · 4.94 KB · SHA-256 9379eebcc82d…2241 · Civitai

Download file

Source excerpts

1 excerpt

NoteOct 17civitai.com/models/2037986

Source context: 23 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B