>docs/models

Models

Nohuman AI provides two video generation models: nohuman-x33 for text-to-video and image-to-video, and nohuman-x39 for motion control generation.

# nohuman-x33T2V + I2V

Our flagship video generation model. nohuman-x33 delivers cinematic-quality video from text prompts or reference images with support for multiple aspect ratios, optional audio, and CFG scale control.

Capabilities

Text-to-Video, Image-to-Video

Endpoint

POST /v1/videos/generate

Durations

5s, 10s

Aspect Ratios

16:9, 9:16, 1:1

Output Format

MP4

Audio

Optional (sound parameter)

TypeDurationPrice
T2V (with audio)5s$0.70
T2V (with audio)10s$1.40
I2V5s$0.21
I2V10s$0.42

Prompt Tips

For best results, describe the scene, camera movement, lighting, and style explicitly. Use the negative_prompt parameter to exclude unwanted elements.

"A cinematic dolly shot through a misty forest at dawn, volumetric lighting, 4K film grain"

"Close-up of a woman sipping coffee in a cozy cafe, shallow depth of field, warm tones"

"Aerial drone shot of ocean waves crashing on rocky coastline, golden hour"

# nohuman-x39MOTION CONTROL

nohuman-x39 enables motion control video generation. Transfer the motion from a reference video onto a character from a reference image, creating a new video where the character performs the actions from the source video.

Capability

Motion Control (Image + Video)

Endpoint

POST /v1/videos/motion-control

Durations

3s, 5s, 10s, 20s, 30s

Output Format

MP4

Inputs Required

image URL + video URL

Audio

Optional (keep_original_sound)

DurationPrice
3s$0.378
5s$0.63
10s$1.26
20s$2.52
30s$3.78

# API Parameters — nohuman-x33

ParameterTypeOptions
promptstringRequired. Scene description
negative_promptstringOptional. Exclude unwanted elements
aspect_ratiostring"16:9" (default), "9:16", "1:1"
durationnumber5 (default), 10
cfg_scalenumber0 to 1 (default 0.5). Guidance strength
soundbooleanEnable audio generation (default false)
image_urlstringOptional. Reference image URL for I2V

# API Parameters — nohuman-x39

ParameterTypeOptions
imagestringRequired. Character image URL
videostringRequired. Motion reference video URL
character_orientationstring"image" or "video" (optional)
promptstringOptional. Additional scene description
negative_promptstringOptional. Exclude unwanted elements
keep_original_soundbooleanKeep audio from reference video (default false)

# Competitive Comparison

Featurenohuman-x33/x39SoraVeoRunway
Max duration30s (X39)1 min8s4s
Aspect ratios16:9, 9:16, 1:116:916:916:9
Text-to-videoYesYesYesYes
Image-to-videoYesYesYesYes
Motion controlYes (X39)NoNoNo
API accessYesWaitlistLimitedYes
Pricingfrom $0.21N/AN/A$0.05/s

# Response Format

// POST /v1/videos/generate response:
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "nohuman-x33",
  "status": "created",
  "poll_url": "/v1/videos/generations/gen_a1b2c3d4e5f6"
}

// POST /v1/videos/motion-control response:
{
  "id": "gen_mc_x7y8z9",
  "model": "nohuman-x39",
  "status": "created",
  "poll_url": "/v1/videos/generations/gen_mc_x7y8z9"
}

// GET /v1/videos/generations/{id} when completed:
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "nohuman-x33",
  "status": "completed",
  "result": {
    "url": "https://cdn.nohuman.studio/v/gen_a1b2c3d4.mp4",
    "format": "mp4"
  }
}

SYS :: models :: reference guide