Skip to main content
ArtEmotion
Video

CogVideoX 5B (I2V)

Credit-based pricing. Supports image-to-video.

Output
video
Aspect ratio
16:9, 9:16, 1:1, 4:3, 3:4

Inputs

  • Start image (required)

Example prompt

Ancient waterfall cascading into an emerald jungle pool, lush tropical ferns, mist rising, water churning catching the light
Try this prompt →
LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/cogvideox-5b/image-to-video.

POST/api/v1/generate21 fields · 3 required
FieldTypeRequirementContract
model_idconstantRequiredArtEmotion model identifier.
extraobjectOptionalModel-specific settings may also be nested here.
max_creditsnumberOptionalReject before submission if the estimated list price exceeds this cap. · Range: 1–…
webhook_urlstringOptionalFormat: uri
webhook_secretstringOptionalOptional model input.
folder_idstringOptionalOptional model input.
promptstringRequiredOptional model input.
guidance_scalenumberOptionalThe CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related video to show · Default: 7 · Range: 0–20
negative_promptstringOptionalThe negative prompt to generate video from · Default:
seedintegerOptionalThe same seed and the same prompt given to the same version of the model will output the same video every time.
use_rifebooleanOptionalUse RIFE for video interpolation · Default: true
export_fpsnumberOptionalThe target FPS of the video · Default: 16 · Range: 4–32
num_inference_stepsnumberOptionalThe number of inference steps to perform. · Default: 50 · Range: 1–50
lora_pathstringOptionalURL or Hugging Face path to LoRA weights.
lora_scalenumberOptionalStrength of the LoRA effect. · Default: 1 · Range: 0–4
lora_path_2stringOptionalURL or Hugging Face path to a second LoRA.
lora_scale_2numberOptionalStrength of the second LoRA. · Default: 1 · Range: 0–4
lora_path_3stringOptionalURL or Hugging Face path to a third LoRA.
lora_scale_3numberOptionalStrength of the third LoRA. · Default: 1 · Range: 0–4
aspect_ratiostringOptionalAllowed: 16:9, 9:16, 1:1, 4:3, 3:4
image_urlstringRequiredFormat: uri
Minimal request example
{
  "model_id": "fal-ai/cogvideox-5b/image-to-video",
  "prompt": "Ancient waterfall cascading into an emerald jungle pool, lush tropical ferns, mist rising, water churning catching the light",
  "image_url": "https://example.com/image"
}
Raw JSON Schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fcogvideox-5b%2Fimage-to-video",
  "title": "CogVideoX 5B (I2V) generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/cogvideox-5b/image-to-video.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/cogvideox-5b/image-to-video",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "guidance_scale": {
      "title": "Guidance Scale",
      "description": "The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related video to show",
      "default": 7,
      "type": "number",
      "minimum": 0,
      "maximum": 20,
      "multipleOf": 0.1
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "description": "The negative prompt to generate video from",
      "default": "",
      "type": "string"
    },
    "seed": {
      "title": "Seed",
      "description": "The same seed and the same prompt given to the same version of the model will output the same video every time.",
      "type": "integer"
    },
    "use_rife": {
      "title": "Use Rife",
      "description": "Use RIFE for video interpolation",
      "default": true,
      "type": "boolean"
    },
    "export_fps": {
      "title": "Export Fps",
      "description": "The target FPS of the video",
      "default": 16,
      "type": "number",
      "minimum": 4,
      "maximum": 32,
      "multipleOf": 1
    },
    "num_inference_steps": {
      "title": "Num Inference Steps",
      "description": "The number of inference steps to perform.",
      "default": 50,
      "type": "number",
      "minimum": 1,
      "maximum": 50,
      "multipleOf": 1
    },
    "lora_path": {
      "title": "LoRA Path",
      "description": "URL or Hugging Face path to LoRA weights.",
      "type": "string"
    },
    "lora_scale": {
      "title": "LoRA Scale",
      "description": "Strength of the LoRA effect.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_2": {
      "title": "LoRA Path 2",
      "description": "URL or Hugging Face path to a second LoRA.",
      "type": "string"
    },
    "lora_scale_2": {
      "title": "LoRA Scale 2",
      "description": "Strength of the second LoRA.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_3": {
      "title": "LoRA Path 3",
      "description": "URL or Hugging Face path to a third LoRA.",
      "type": "string"
    },
    "lora_scale_3": {
      "title": "LoRA Scale 3",
      "description": "Strength of the third LoRA.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:3",
        "3:4"
      ]
    },
    "image_url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model_id",
    "prompt",
    "image_url"
  ],
  "additionalProperties": false
}

FAQ

How much does CogVideoX 5B (I2V) cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if CogVideoX 5B (I2V) fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call CogVideoX 5B (I2V) from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/cogvideox-5b/image-to-video". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with CogVideoX 5B (I2V)?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.