Sign In

Digital human from one image + audio - OmniRef 8-step (ComfyUI)

Updated: Nov 21, 2026

comfyuih3minimaxdigital-human

Download

1 variant available

Config Other

__________OmniRef____.json

56.81 KB

Verified:

Type
Workflows
Stats

12

Reviews

No reviews yet

Published

Nov 21, 2026

Base Model
Hash
AutoV2380B1F39B7

The FLUX.1 [dev] Model is licensed by Black Forest Labs Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs Inc.

IN NO EVENT SHALL BLACK FOREST LABS INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

71b19a92-96ff-45e2-92bf-59d7bd7bf54b.png

MiniMax H3 digital human: one reference image plus an audio track drives a talking head, OmniRef keeps identity stable, 8-step schedule.

Try online: https://www.runninghub.cn/post/2119383916514725890/?inviteCode=rh-v1111

2K finish: https://www.runninghub.cn/post/2119383924827844609/?inviteCode=rh-v1111

Episode: https://youtu.be/2cgAuD5c_vI

Limits: identity drifts on big head turns; clean audio required; not full-body animation.