bot/image-generate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(image): force openai mode for gpt-image-2 scripts

Browse Source
This commit is contained in:
zhangheng
2026-05-18 13:55:56 +08:00
parent ed189dd54b
commit 45b6ce2063
4 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -28,6 +28,8 @@ bash scripts/run_openai_gpt_image2_edit.sh
bash scripts/run_openai_gpt_image2_multi.sh bash scripts/run_openai_gpt_image2_multi.sh
``` ```
这两个 OpenAI 脚本会强制 `IMAGE_REQUEST_STYLE=openai`，不会沿用 `.env` 里的 `apicodex`。
## 配置 ## 配置
复制 `.env.example` 为 `.env`，按需填写： 复制 `.env.example` 为 `.env`，按需填写：

1
docs/usage.md
View File

@@ -305,6 +305,7 @@ else:
- 这两个 direct test 会自动忽略 `.env` 里的 `REFERENCE_IMAGE` 和 `MASK_IMAGE`，默认走纯生成流程。 - 这两个 direct test 会自动忽略 `.env` 里的 `REFERENCE_IMAGE` 和 `MASK_IMAGE`，默认走纯生成流程。
- 如果要走 OpenAI-compatible 的 `gpt-image-2` 图生图，运行 `bash scripts/run_openai_gpt_image2_edit.sh`。 - 如果要走 OpenAI-compatible 的 `gpt-image-2` 图生图，运行 `bash scripts/run_openai_gpt_image2_edit.sh`。
- 如果要走多图参考生成多图，运行 `bash scripts/run_openai_gpt_image2_multi.sh`。 - 如果要走多图参考生成多图，运行 `bash scripts/run_openai_gpt_image2_multi.sh`。
- 这两个 OpenAI 脚本会强制 `IMAGE_REQUEST_STYLE=openai`，不会沿用 `.env` 里的 `apicodex`。
- 图生图可通过环境变量传参考图： - 图生图可通过环境变量传参考图：
`REFERENCE_IMAGE=./input.png`，或 `REFERENCE_IMAGE_URL=https://example.com/input.png`。 `REFERENCE_IMAGE=./input.png`，或 `REFERENCE_IMAGE_URL=https://example.com/input.png`。
- 如需 mask，可额外传： - 如需 mask，可额外传：

2
scripts/run_openai_gpt_image2_edit.sh
View File

@@ -46,7 +46,7 @@ done
unset http_proxy https_proxy all_proxy HTTP_PROXY HTTPS_PROXY ALL_PROXY unset http_proxy https_proxy all_proxy HTTP_PROXY HTTPS_PROXY ALL_PROXY
export IMAGE_REQUEST_STYLE="${IMAGE_REQUEST_STYLE:-openai}" export IMAGE_REQUEST_STYLE="openai"
export IMAGE_MODEL="${IMAGE_MODEL:-gpt-image-2}" export IMAGE_MODEL="${IMAGE_MODEL:-gpt-image-2}"
export IMAGE_SIZE="${IMAGE_SIZE:-1024x1024}" export IMAGE_SIZE="${IMAGE_SIZE:-1024x1024}"
export IMAGE_REQUEST_TIMEOUT="${IMAGE_REQUEST_TIMEOUT:-900}" export IMAGE_REQUEST_TIMEOUT="${IMAGE_REQUEST_TIMEOUT:-900}"

2
scripts/run_openai_gpt_image2_multi.sh
View File

@@ -59,7 +59,7 @@ done
unset http_proxy https_proxy all_proxy HTTP_PROXY HTTPS_PROXY ALL_PROXY unset http_proxy https_proxy all_proxy HTTP_PROXY HTTPS_PROXY ALL_PROXY
export IMAGE_REQUEST_STYLE="${IMAGE_REQUEST_STYLE:-openai}" export IMAGE_REQUEST_STYLE="openai"
export IMAGE_MODEL="${IMAGE_MODEL:-gpt-image-2}" export IMAGE_MODEL="${IMAGE_MODEL:-gpt-image-2}"
export IMAGE_SIZE="${IMAGE_SIZE:-1024x1024}" export IMAGE_SIZE="${IMAGE_SIZE:-1024x1024}"
export IMAGE_RESPONSE_DIR="${IMAGE_RESPONSE_DIR:-outputs/image-multi-runs}" export IMAGE_RESPONSE_DIR="${IMAGE_RESPONSE_DIR:-outputs/image-multi-runs}"