Image generation API

Youchuan

Youchuan v8.1 & v8.2 — text-to-image, image-to-image, style transfer, blending, and background removal.

Provider: Youchuan10 models

Available models

Model key	Display name	Capability	Atlas Cloud slug
`youchuan_v8_2_t2i`	Youchuan v8.2 T2I	text-to-image	youchuan/v8.2/text-to-image
`youchuan_v8_2_i2i`	Youchuan v8.2 I2I	image-to-image	youchuan/v8.2/image-to-image
`youchuan_v8_2_style_transfer`	Youchuan v8.2 Style Transfer	style-transfer	youchuan/v8.2/style-transfer
`youchuan_v8_2_blend`	Youchuan v8.2 Blend	blend	youchuan/v8.2/blend
`youchuan_v8_2_remove_bg`	Youchuan v8.2 Remove BG	remove-background	youchuan/v8.2/remove-background
`youchuan_v8_1_t2i`	Youchuan v8.1 T2I	text-to-image	youchuan/v8.1/text-to-image
`youchuan_v8_1_i2i`	Youchuan v8.1 I2I	image-to-image	youchuan/v8.1/image-to-image
`youchuan_v8_1_style_transfer`	Youchuan v8.1 Style Transfer	style-transfer	youchuan/v8.1/style-transfer
`youchuan_v8_1_blend`	Youchuan v8.1 Blend	blend	youchuan/v8.1/blend
`youchuan_v8_1_remove_bg`	Youchuan v8.1 Remove BG	remove-background	youchuan/v8.1/remove-background

Endpoint

POST /api/generate

Request body

Parameter	Type	Required	Description
`modelKey`	string	✓	One of the model keys listed above
`prompt`	string	✓	Text description of the image to generate
`inputUrl`	string		Input image URL (for edit/i2i models)
`aspectRatio`	string		`"1:1"`, `"16:9"`, `"9:16"`, etc.
`imageQuality`	string		`"Low"`, `"Medium"`, `"High"`
`styleRef`	string \| string[]		Style reference image URL(s)
`charRef`	string \| string[]		Character reference image URL(s)
`brandId`	string		Brand DNA ID for brand-consistent generation

Code example

curl -X POST https://api.oyefilmy.com/api/generate \
  -H "Authorization: Bearer of_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelKey": "youchuan_v8_2_t2i",
    "prompt": "A vibrant pop art portrait of a cat wearing sunglasses"
  }'

Response

{
  "success": true,
  "predictionId": "pred_abc123...",
  "status": "processing",
  "model": "youchuan/v8.2/text-to-image",
  "creditCost": 5
}

Style transfer requires a styleRef URL. Blend combines two to five images. Remove BG extracts the subject from the background. V8.2 models support HD generation, stylize, chaos and weird controls.

← All image models

Back to image generation overview

Webhooks

Receive results automatically