Назад към всички

yollomi-ai-api

// AI image generator skill (image, image generation). Multi-model image generator for Yollomi to generate AI images via one unified API endpoint. Requires YOLLOMI_API_KEY.

$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
nameyollomi-ai-api
descriptionAI image generator skill (image, image generation). Multi-model image generator for Yollomi to generate AI images via one unified API endpoint. Requires YOLLOMI_API_KEY.
metadata[object Object]

Yollomi AI API Skill

Generates images and videos via the Yollomi API. All models use a single unified endpoint with different modelId parameters.

Setup

  1. API Key: Set YOLLOMI_API_KEY (environment variable).
  2. Base URL (optional): Set YOLLOMI_BASE_URL to override API host (default: https://yollomi.com).

Unified Endpoint

POST /api/v1/generate

Headers: Authorization: Bearer ${YOLLOMI_API_KEY} or X-API-Key: ${YOLLOMI_API_KEY}
Content-Type: application/json

Body:

  • type (required): "image" or "video"
  • modelId (required): Model identifier
  • Additional params depend on model (prompt, imageUrl, etc.)

Response (image): { images: string[], remainingCredits: number }
Response (video): { video: string, remainingCredits: number }

List Models

GET /api/v1/models

Returns all available image and video modelIds.

Common Examples

Generate image (Flux):

curl -X POST "${YOLLOMI_BASE_URL:-https://yollomi.com}/api/v1/generate" \
  -H "Authorization: Bearer $YOLLOMI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","modelId":"flux","prompt":"A cat in a hat","aspectRatio":"1:1"}'

Remove background:

curl -X POST "${YOLLOMI_BASE_URL:-https://yollomi.com}/api/v1/generate" \
  -H "Authorization: Bearer $YOLLOMI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","modelId":"remove-bg","imageUrl":"https://example.com/photo.jpg"}'

Generate video:

curl -X POST "${YOLLOMI_BASE_URL:-https://yollomi.com}/api/v1/generate" \
  -H "Authorization: Bearer $YOLLOMI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","modelId":"kling-2-1","prompt":"A cat walking in the rain"}'

Aspect Ratio (aspectRatio)

Supported aspect ratios for text-to-image models:

ratiodescription
1:1Square (default)
16:9Landscape
9:16Portrait

Image ModelIds

modelIdCreditsRequiredaspectRatio
flux4/imgprompt1:1, 16:9, 9:16
flux-schnell2/imgpromptsame as above
flux-2-pro15/imgpromptsame as above
remove-bg0imageUrl-
nano-banana4prompt1:1, 16:9, 9:16
nano-banana-pro15promptsame as above
flux-kontext-pro4promptsame as above
z-image-turbo1promptwidth, height
imagen-4-ultra6promptsame as above
image-4-fast3promptsame as above
ideogram-v3-turbo3promptsame as above
stable-diffusion-3-5-large7/imgpromptsame as above
seedream-4-54promptsame as above
object-remover3image, mask-
face-swap3swapImage, inputImage-
image-upscaler1imageUrl, scale-
photo-restoration4imageUrl-
qwen-image-edit3image, prompt-
qwen-image-edit-plus3image, prompt-
virtual-try-on3clothImage, personImage-
ai-background-generator5imageUrlprompt

Video ModelIds

modelIdCredits
openai-sora-2~50+
google-veo-310
google-veo-3-fast9
google-veo-3-110
google-veo-3-1-fast9
kling-2-19
kling-v2-6-motion-control7/sec
minimax-hailuo-2-39
minimax-hailuo-2-3-fast9
bytedance-seedance-1-pro-fast8
runway-gen4-turbovaries
pixverse-59
wan-2-5-i2v9
wan-2-5-t2v9
wan-2-6-i2v29
wan-2-6-t2v29

OpenClaw Tools

ToolDescription
yollomi.generateGenerate image or video. Params: type, modelId, prompt, imageUrl, aspectRatio, numOutputs, inputs (video)
yollomi.listModelsList all available image and video models with credit costs. No auth required.

Workflow

  1. List models → yollomi.listModels() or GET /api/v1/models
  2. Generate image → yollomi.generate({ type: "image", modelId, prompt, ... })
  3. Generate video → yollomi.generate({ type: "video", modelId, prompt, inputs: { ... } })
  4. 401/402 → Check API key and credits

Reference

Full model list and params: models-reference.md or GET /api/v1/models