AIIA Ditto Sampler is a ComfyUI node in the AIIA/Ditto category from ComfyUI_AIIA. Inputs: pipe, ref_image, audio, sampling_steps. Outputs: IMAGE, AUDIO…

Tired of OOM errors and tedious file management? The AIIA Node Suite delivers the ultimate workflow overhaul, headlined by the AIIA Media Browser: a high-performance file hub fully integrated into ComfyUI. Instantly preview images, videos, and audio, and experience ultimate smoothness thanks to smart caching and virtual scrolling, even with tens of thousands of files. It also features a powerful fullscreen viewer, rich tooltip previews, and flexible sorting. Alongside the browser, our Video Combine node fundamentally solves memory bottlenecks in long video generation. By streaming frames from disk, you can create videos of virtually unlimited length, making OOM errors a thing of the past. The suite also includes OOM-safe FLOAT video generation, advanced audio processing, and other utilities, providing a complete end-to-end solution from content creation to asset management.

ComfyUI_AIIA

pipe

ref_image

audio

sampling_steps

crop_scale

drive_eye

chk_eye_blink

smo_k_d

hd_rot_p

hd_rot_y

hd_rot_r

speech_pitch

mouth_amp

blink_amp

relax_on_silence

ref_threshold

blink_mode

speech_only_blink

silence_release

mouth_smoothing

save_to_disk

seed

AIIA_DittoSampler

images

frames_dir

AIIA Ditto Sampler

Name	Type	Default	Description
pipe	DITTO_PIPE		—
ref_image	IMAGE		—
audio	AUDIO		—
sampling_steps	INT	501–100	—
fps	FLOAT	25.00015–60	—
crop_scale	FLOAT	2.31–5	—
emo	COMBO	Neutral	8 options: Neutral, Angry, Disgust, Fear, Happy, Sad, +2
drive_eye	BOOLEAN	true	—
chk_eye_blink	BOOLEAN	true	—
smo_k_d	INT	51–9	—
hd_rot_p	FLOAT	0-30–30	—
hd_rot_y	FLOAT	0-30–30	—
hd_rot_r	FLOAT	0-30–30	—
speech_pitch	FLOAT	0-20–20	Pitch offset applied ONLY during speech. Positive = Look Down, Negative = Look Up.
mouth_amp	FLOAT	1.000–2	—
blink_amp	FLOAT	1.000–2	—
relax_on_silence	BOOLEAN	true	—
ref_threshold	FLOAT	0.0050–1	—
blink_mode	COMBO	Natural	4 options: Natural, Fast, Slow, None
speech_only_blink	BOOLEAN	false	—
silence_release	COMBO	Natural (0.8s)	3 options: Natural (0.8s), Fast (0.5s), Deep (1.3s)
mouth_smoothing	COMBO	Normal	5 options: Normal, None (Raw), Light, Heavy, Custom (Manual)
save_to_disk	COMBO	Memory (Default)	Memory: Fast, all frames in RAM. Disk: Slower, but handles 1000+ frames without OOM. Auto: Uses Disk if 'frames_dir' output is connected.
seed	INT	00–18446744073709550000	—

Name	Type	Description
images	IMAGE	—
audio	AUDIO	—
frames_dir	STRING	—

AIIA Ditto Sampler

Inputs (24)

Outputs (3)