java/resources/images/methods/edit/index.md

Create image edit

ImagesResponse images().edit(ImageEditParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /images/edits

Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini, and chatgpt-image-latest) and dall-e-2.

Parameters

ImageEditParams params
- Image image
  
  The image(s) to edit. Must be a supported image file or an array of images.
  
  For the GPT image models (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, and chatgpt-image-latest), each image should be a png, webp, or jpg file less than 50MB. You can provide up to 16 images.
  
  For dall-e-2, you can only provide one image, and it should be a square png file less than 4MB.
  - String
  - List<String>
- String prompt
  
  A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2, and 32000 characters for the GPT image models.
- Optional<Background> background
  
  Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.
  
  gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.
  
  If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
  - TRANSPARENT("transparent")
  - OPAQUE("opaque")
  - AUTO("auto")
- Optional<InputFidelity> inputFidelity
  
  Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
  - HIGH("high")
  - LOW("low")
- Optional<String> mask
  
  An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.
- Optional<ImageModel> model
  
  The model to use for image generation. One of dall-e-2 or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, or chatgpt-image-latest). Defaults to gpt-image-1.5.
- Optional<Long> n
  
  The number of images to generate. Must be between 1 and 10.
- Optional<Long> outputCompression
  
  The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the webp or jpeg output formats, and defaults to 100.
- Optional<OutputFormat> outputFormat
  
  The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of png, jpeg, or webp. The default value is png.
  - PNG("png")
  - JPEG("jpeg")
  - WEBP("webp")
- Optional<Long> partialImages
  
  The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event.
  
  Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly.
- Optional<Quality> quality
  
  The quality of the image that will be generated for GPT image models. Defaults to auto.
  - STANDARD("standard")
  - LOW("low")
  - MEDIUM("medium")
  - HIGH("high")
  - AUTO("auto")
- Optional<ResponseFormat> responseFormat
  
  The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for dall-e-2 (default is url for dall-e-2), as GPT image models always return base64-encoded images.
  - URL("url")
  - B64_JSON("b64_json")
- Optional<Size> size
  
  The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
  - _256X256("256x256")
  - _512X512("512x512")
  - _1024X1024("1024x1024")
  - _1536X1024("1536x1024")
  - _1024X1536("1024x1536")
  - AUTO("auto")
- Optional<String> user
  
  A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

class ImagesResponse:

The response from the image generation endpoint.
- long created
  
  The Unix timestamp (in seconds) of when the image was created.
- Optional<Background> background
  
  The background parameter used for the image generation. Either transparent or opaque.
  - TRANSPARENT("transparent")
  - OPAQUE("opaque")
- Optional<List<Image>> data
  
  The list of generated images.
  - Optional<String> b64Json
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - Optional<String> revisedPrompt
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - Optional<String> url
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- Optional<OutputFormat> outputFormat
  
  The output format of the image generation. Either png, webp, or jpeg.
  - PNG("png")
  - WEBP("webp")
  - JPEG("jpeg")
- Optional<Quality> quality
  
  The quality of the image generated. Either low, medium, or high.
  - LOW("low")
  - MEDIUM("medium")
  - HIGH("high")
- Optional<Size> size
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - _1024X1024("1024x1024")
  - _1024X1536("1024x1536")
  - _1536X1024("1536x1024")
- Optional<Usage> usage
  
  For gpt-image-1 only, the token usage information for the image generation.
  - long inputTokens
    
    The number of tokens (images and text) in the input prompt.
  - InputTokensDetails inputTokensDetails
    
    The input tokens detailed information for the image generation.
    - long imageTokens
      
      The number of image tokens in the input prompt.
    - long textTokens
      
      The number of text tokens in the input prompt.
  - long outputTokens
    
    The number of output tokens generated by the model.
  - long totalTokens
    
    The total number of tokens (images and text) used for the image generation.
  - Optional<OutputTokensDetails> outputTokensDetails
    
    The output token details for the image generation.
    - long imageTokens
      
      The number of image output tokens generated by the model.
    - long textTokens
      
      The number of text output tokens generated by the model.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.ImageEditParams;
import com.openai.models.images.ImagesResponse;
import java.io.ByteArrayInputStream;
import java.io.InputStream;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        ImageEditParams params = ImageEditParams.builder()
            .image(new ByteArrayInputStream("Example data".getBytes()))
            .prompt("A cute baby sea otter wearing a beret")
            .build();
        ImagesResponse imagesResponse = client.images().edit(params);
    }
}

Response

{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

java/resources/images/methods/edit/index.md +305 −0 created

1## Create image edit

3`ImagesResponse images().edit(ImageEditParamsparams, RequestOptionsrequestOptions = RequestOptions.none())`

5**post** `/images/edits`

7Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models (`gpt-image-1.5`, `gpt-image-1`, `gpt-image-1-mini`, and `chatgpt-image-latest`) and `dall-e-2`.

9### Parameters

11- `ImageEditParams params`

13 - `Image image`

15 The image(s) to edit. Must be a supported image file or an array of images.

17 For the GPT image models (`gpt-image-1`, `gpt-image-1-mini`,

18 `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, and

19 `chatgpt-image-latest`), each image should be a `png`, `webp`, or

20 `jpg` file less than 50MB. You can provide up to 16 images.

22 For `dall-e-2`, you can only provide one image, and it should be a

23 square `png` file less than 4MB.

25 - `String`

27 - `List<String>`

29 - `String prompt`

31 A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for the GPT image models.

33 - `Optional<Background> background`

35 Allows to set transparency for the background of the generated image(s).

36 This parameter is only supported for GPT image models that support

37 transparent backgrounds. Must be one of `transparent`, `opaque`, or

38 `auto` (default value). When `auto` is used, the model will

39 automatically determine the best background for the image.

41 `gpt-image-2` and `gpt-image-2-2026-04-21` do not support

42 transparent backgrounds. Requests with `background` set to

43 `transparent` will return an error for these models; use `opaque` or

44 `auto` instead.

46 If `transparent`, the output format needs to support transparency,

47 so it should be set to either `png` (default value) or `webp`.

49 - `TRANSPARENT("transparent")`

51 - `OPAQUE("opaque")`

53 - `AUTO("auto")`

55 - `Optional<InputFidelity> inputFidelity`

57 Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`.

59 - `HIGH("high")`

61 - `LOW("low")`

63 - `Optional<String> mask`

65 An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.

67 - `Optional<ImageModel> model`

69 The model to use for image generation. One of `dall-e-2` or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, or `chatgpt-image-latest`). Defaults to `gpt-image-1.5`.

71 - `Optional<Long> n`

73 The number of images to generate. Must be between 1 and 10.

75 - `Optional<Long> outputCompression`

77 The compression level (0-100%) for the generated images. This parameter

78 is only supported for the GPT image models with the `webp` or `jpeg` output

79 formats, and defaults to 100.

81 - `Optional<OutputFormat> outputFormat`

83 The format in which the generated images are returned. This parameter is

84 only supported for the GPT image models. Must be one of `png`, `jpeg`, or `webp`.

85 The default value is `png`.

87 - `PNG("png")`

89 - `JPEG("jpeg")`

91 - `WEBP("webp")`

93 - `Optional<Long> partialImages`

95 The number of partial images to generate. This parameter is used for

96 streaming responses that return partial images. Value must be between 0 and 3.

97 When set to 0, the response will be a single image sent in one streaming event.

99 Note that the final image may be sent before the full number of partial images

100 are generated if the full image is generated more quickly.

101

102 - `Optional<Quality> quality`

103

104 The quality of the image that will be generated for GPT image models. Defaults to `auto`.

105

106 - `STANDARD("standard")`

107

108 - `LOW("low")`

109

110 - `MEDIUM("medium")`

111

112 - `HIGH("high")`

113

114 - `AUTO("auto")`

115

116 - `Optional<ResponseFormat> responseFormat`

117

118 The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2` (default is `url` for `dall-e-2`), as GPT image models always return base64-encoded images.

119

120 - `URL("url")`

121

122 - `B64_JSON("b64_json")`

123

124 - `Optional<Size> size`

125

126 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

127

128 - `_256X256("256x256")`

129

130 - `_512X512("512x512")`

131

132 - `_1024X1024("1024x1024")`

133

134 - `_1536X1024("1536x1024")`

135

136 - `_1024X1536("1024x1536")`

137

138 - `AUTO("auto")`

139

140 - `Optional<String> user`

141

142 A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

143

144### Returns

145

146- `class ImagesResponse:`

147

148 The response from the image generation endpoint.

149

150 - `long created`

151

152 The Unix timestamp (in seconds) of when the image was created.

153

154 - `Optional<Background> background`

155

156 The background parameter used for the image generation. Either `transparent` or `opaque`.

157

158 - `TRANSPARENT("transparent")`

159

160 - `OPAQUE("opaque")`

161

162 - `Optional<List<Image>> data`

163

164 The list of generated images.

165

166 - `Optional<String> b64Json`

167

168 The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if `response_format` is set to `b64_json` for `dall-e-2` and `dall-e-3`.

169

170 - `Optional<String> revisedPrompt`

171

172 For `dall-e-3` only, the revised prompt that was used to generate the image.

173

174 - `Optional<String> url`

175

176 When using `dall-e-2` or `dall-e-3`, the URL of the generated image if `response_format` is set to `url` (default value). Unsupported for the GPT image models.

177

178 - `Optional<OutputFormat> outputFormat`

179

180 The output format of the image generation. Either `png`, `webp`, or `jpeg`.

181

182 - `PNG("png")`

183

184 - `WEBP("webp")`

185

186 - `JPEG("jpeg")`

187

188 - `Optional<Quality> quality`

189

190 The quality of the image generated. Either `low`, `medium`, or `high`.

191

192 - `LOW("low")`

193

194 - `MEDIUM("medium")`

195

196 - `HIGH("high")`

197

198 - `Optional<Size> size`

199

200 The size of the image generated. Either `1024x1024`, `1024x1536`, or `1536x1024`.

201

202 - `_1024X1024("1024x1024")`

203

204 - `_1024X1536("1024x1536")`

205

206 - `_1536X1024("1536x1024")`

207

208 - `Optional<Usage> usage`

209

210 For `gpt-image-1` only, the token usage information for the image generation.

211

212 - `long inputTokens`

213

214 The number of tokens (images and text) in the input prompt.

215

216 - `InputTokensDetails inputTokensDetails`

217

218 The input tokens detailed information for the image generation.

219

220 - `long imageTokens`

221

222 The number of image tokens in the input prompt.

223

224 - `long textTokens`

225

226 The number of text tokens in the input prompt.

227

228 - `long outputTokens`

229

230 The number of output tokens generated by the model.

231

232 - `long totalTokens`

233

234 The total number of tokens (images and text) used for the image generation.

235

236 - `Optional<OutputTokensDetails> outputTokensDetails`

237

238 The output token details for the image generation.

239

240 - `long imageTokens`

241

242 The number of image output tokens generated by the model.

243

244 - `long textTokens`

245

246 The number of text output tokens generated by the model.

247

248### Example

249

250```java

251package com.openai.example;

252

253import com.openai.client.OpenAIClient;

254import com.openai.client.okhttp.OpenAIOkHttpClient;

255import com.openai.models.images.ImageEditParams;

256import com.openai.models.images.ImagesResponse;

257import java.io.ByteArrayInputStream;

258import java.io.InputStream;

259

260public final class Main {

261 private Main() {}

262

263 public static void main(String[] args) {

264 OpenAIClient client = OpenAIOkHttpClient.fromEnv();

265

266 ImageEditParams params = ImageEditParams.builder()

267 .image(new ByteArrayInputStream("Example data".getBytes()))

268 .prompt("A cute baby sea otter wearing a beret")

269 .build();

270 ImagesResponse imagesResponse = client.images().edit(params);

271 }

272}

273```

274

275#### Response

276

277```json

278{

279 "created": 0,

280 "background": "transparent",

281 "data": [

282 {

283 "b64_json": "b64_json",

284 "revised_prompt": "revised_prompt",

285 "url": "https://example.com"

286 }

287 ],

288 "output_format": "png",

289 "quality": "low",

290 "size": "1024x1024",

291 "usage": {

292 "input_tokens": 0,

293 "input_tokens_details": {

294 "image_tokens": 0,

295 "text_tokens": 0

296 },

297 "output_tokens": 0,

298 "total_tokens": 0,

299 "output_tokens_details": {

300 "image_tokens": 0,

301 "text_tokens": 0

302 }

303 }

304}

305```