메인 콘텐츠로 건너뛰기
POST
/api/v1/image/edit
이것은 실험적 엔드포인트이며 변경될 수 있습니다.
가격: 이미지 편집 가격은 모델에 따라 다릅니다. 기본 모델(firered-image-edit)은 편집당 $0.04입니다. 사용 가능한 모든 편집 모델과 가격은 모델 엔드포인트를 참조하세요.

품질 등급

/image/edit는 quality 매개변수를 허용하지 않으며, 보내면 400이 반환됩니다. 이 엔드포인트의 편집은 모델의 기본 등급(gpt-image-2-edit의 경우 high)으로 청구됩니다. 등급(low, medium, high)을 선택하려면 /image/multi-edit를 사용하세요. 이 엔드포인트는 지원하는 모델에서 quality를 허용합니다. 등급별 가격(1K/2K/4K × low/medium/high)은 모델 엔드포인트의 model_spec.pricing.quality 아래에 있으며 가격 개요에 나열되어 있습니다.

Postman 컬렉션

추가 예제는 이 Postman 컬렉션을 참조하세요.
콘텐츠 정책은 편집 모델에 따라 다릅니다. 선택한 모델의 정책을 위반하는 요청은 거부됩니다.

인증

Authorization
string
header
필수

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

본문

Edit an image based on the supplied prompt.

image
필수

The image to edit. Can be either a file upload, a base64-encoded string, or a URL starting with http:// or https://. Image dimensions must be at least 65536 pixels and must not exceed 33177600 pixels. File size must be less than 25MB.

prompt
string
필수

The text directions to edit or modify the image. Short, descriptive prompts work best (e.g., "remove the tree", "change the sky to sunrise"). Character limit is model specific and is listed in the promptCharacterLimit setting in the model list endpoint.

Required string length: 1 - 32768
예시:

"Change the color of the sky to a sunrise"

anon_user_id
string

Optional identifier for the API customer's end user. Combined with the Venice user id when attributing the request to upstream providers. Distinct from the discarded OpenAI user field. Must be printable ASCII and must not contain ||.

Required string length: 1 - 128
Pattern: ^[\x20-\x7E]+$
예시:

"end-user-123"

aspect_ratio
enum<string>

The aspect ratio for the output image. Use 'auto' or omit this parameter to infer the closest supported aspect ratio from the input image when explicit sizing is required by the model. Supported values vary by model - check GET /api/v1/models for model-specific options.

사용 가능한 옵션:
auto,
1:1,
3:2,
16:9,
21:9,
9:16,
2:3,
3:4,
4:3,
4:5
예시:

"16:9"

disable_prompt_optimization_thinking
boolean

Skip the model's prompt-optimization thinking step for faster generation. Only supported by models with supportsOptimizePromptThinking; ignored by others. Omit to use the model default.

예시:

false

enhance_prompt
boolean

Rewrite the edit prompt using the input image before editing to add clarifying detail. Additional credits are charged when a rewrite is generated. Adds up to ~30 seconds. When enhancement is applied, the final prompt is returned URL-encoded in the x-venice-enhanced-prompt response header. Defaults to false.

예시:

false

resolution
string

Resolution tier for the output image (e.g. "1K", "2K", "4K"). Supported values vary by model - check GET /api/v1/models for model-specific options. Defaults to "1K" when not specified.

Required string length: 1 - 10
예시:

"1K"

model
string
기본값:firered-image-edit

The model ID to use for image editing.

Minimum string length: 1
modelId
enum<string>
지원 중단

Deprecated: Use "model" instead. The model ID to use for image editing.

사용 가능한 옵션:
firered-image-edit,
qwen-edit-uncensored,
grok-imagine-edit,
grok-imagine-quality-edit,
grok-imagine-image-2-0-edit,
qwen-image-2-edit,
qwen-image-2-pro-edit,
wan-2-7-pro-edit,
flux-2-max-edit,
flux-3-image-edit,
gpt-image-2-5-flare-edit,
gpt-image-2-5-sunburst-edit,
gpt-image-2-edit,
gpt-image-1-5-edit,
ideogram-v4-5-edit,
nano-banana-2-edit,
nano-banana-2-1-edit,
nano-banana-pro-edit,
nano-banana-2-lite-edit,
luma-uni-1-edit,
luma-uni-1-max-edit,
muse-image-edit,
seedream-v5-lite-edit,
seedream-v5-pro-edit,
seedream-v4-edit,
qwen-image-3-edit,
qwen-image-3-pro-edit,
qwen-image-2-1-turbo-edit,
qwen-image-2-1-pro-edit
Minimum string length: 1
output_format
enum<string>

Output format for the edited image. Accepts jpeg, jpg, png, or webp. When omitted, the format is inferred from resolution: PNG for 1K edits and JPEG for 2K/4K edits, or PNG at any resolution when transparent_background is true.

사용 가능한 옵션:
jpeg,
png,
webp
예시:

"png"

safe_mode
boolean
기본값:true

Whether to blur images classified as adult content. Defaults to true. Set to false to receive unblurred output. No Pro subscription is required, and the mature filter setting in the Venice app does not affect this. The x-venice-is-blurred response header reports whether the returned image was blurred.

예시:

false

transparent_background
boolean

Return the edited image with a transparent background (alpha channel). Only supported by models with supportsTransparentBackground: true in their constraints (see GET /api/v1/models), and requires output_format png or webp when set; otherwise the request is rejected. Omit or set to false to keep the model default background.

예시:

false

응답

OK

The response is of type file.