Generate images
POST
/302/image/generate
模型名称 | 描述 | 备注 |
---|---|---|
dall-e-3-t2i | DALL·E's text-to-image model | Supported image sizes: 256x256, 512x512, or 1024x1024. Any other value will be treated as 1024x1024 |
dall-e-2-t2i | DALL·E's text-to-image model | Supported image sizes: 256x256, 512x512, or 1024x1024. Any other value will be treated as 1024x1024 |
stable-v1-t2i | Stability.ai's text-to-image v1 model | |
stable-sd2-t2i | Stability.ai's text-to-image sd2 model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3-ultra-t2i | Stability.ai's text-to-image sd3-ultra model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3-t2i | Stability.ai's text-to-image sd3 model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3.5-medium-t2i | Stability.ai's text-to-image sd3.5-medium model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3.5-large-t2i | Stability.ai's text-to-image sd3.5-large model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3-turbo-t2i | Stability.ai's text-to-image sd3-turbo model | Supported aspect ratios: 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21. Any other value will be treated as 1:1 |
stable-sd3-i2i | Stability.ai's image-to-image SD3 model | The aspect_ratio parameter is not supported; the image parameter is required |
stable-sd3.5-medium-i2i | Stability.ai's image-to-image SD3.5-medium model | The aspect_ratio parameter is not supported; the image parameter is required |
stable-sd3.5-large-i2i | Stability.ai's image-to-image SD3.5-large model | The aspect_ratio parameter is not supported; the image parameter is required |
stable-sd3-turbo-i2i | Stability.ai's image-to-image SD3-turbo model | The aspect_ratio parameter is not supported; the image parameter is required |
302ai-sdxl-t2i | SDXL text-to-image model deployed by 302.ai | |
302ai-sdxl-lora-t2i | SDXL-lora text-to-image model deployed by 302.ai | |
302ai-sdxl-lighting-t2i | SDXL-lighting text-to-image model deployed by 302.ai | |
302ai-sdxl-lighting-v2-t2i | SDXL-lighting-v2 text-to-image model deployed by 302.ai | |
302ai-sd3-t2i | SD3 text-to-image model deployed by 302.ai | |
302ai-aura-flow-t2i | aura-flow text-to-image model deployed by 302.ai | |
302ai-kolors-t2i | Open-source text-to-image model (Keling) deployed by 302.ai | |
302ai-kolors-i2i | Open-source image-to-image model (Keling) deployed by 302.ai | The image parameter is required |
302ai-sd35-large-t2i | SD3.5-large text-to-image model deployed by 302.ai | |
302ai-sd35-large-turbo-t2i | SD3.5-large-turbo text-to-image model deployed by 302.ai | |
302ai-sd35-medium-t2i | SD3.5-medium text-to-image model deployed by 302.ai | |
302ai-lumina-t2i | Lumina text-to-image model deployed by 302.ai | |
302ai-omnigen-v1-t2i | omnigen-v1 text-to-image model deployed by 302.ai | |
302ai-playground-v25-t2i | playground-v25 text-to-image model deployed by 302.ai | |
302ai-lora-t2i | lora text-to-image model deployed by 302.ai | |
302ai-lora-t2i | lora text-to-image model deployed by 302.ai | |
flux-pro-1.1-ultra-t2i | Official flux pro-1.1-ultra text-to-image model | |
flux-pro-1.1-t2i | Official flux pro-1.1 text-to-image model | |
flux-pro-t2i | Official flux pro text-to-image model | |
flux-dev-t2i | Official flux pro-dev text-to-image model | |
flux-pro-1.0-fill-t2i | Official flux pro-1.0-fill text-to-image model | |
flux-pro-1.0-canny-t2i | Official flux pro-1.0-canny text-to-image model | |
flux-pro-1.0-depth-t2i | Official flux pro-1.0-depth text-to-image model | |
flux-pro-1.1-ultra-finetuned-t2i | Official flux pro-1.1-ultra-finetuned text-to-image model | |
flux-pro-1.0-finetuned-t2i | Official flux pro-1.0-finetuned text-to-image model | |
flux-pro-1.0-depth-finetuned-t2i | Official flux pro-1.0-depth-finetuned text-to-image model | |
flux-pro-1.0-canny-finetuned-t2i | Official flux pro-1.0-canny-finetuned text-to-image model | |
flux-pro-1.0-fill-finetuned-t2i | Official flux pro-1.0-fill-finetuned text-to-image model | |
302ai-flux-v1.1-ultra-t2i | flux-v1.1-ultra text-to-image model deployed by 302.ai | Supported aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21. Any other value will be treated as 16:9 |
302ai-flux-v1.1-pro-t2i | flux-v1.1-pro text-to-image model deployed by 302.ai | |
302ai-flux-pro-t2i | flux-pro text-to-image model deployed by 302.ai | |
302ai-flux-dev-t2i | flux-dev text-to-image model deployed by 302.ai | |
302ai-flux-schnell-t2i | flux-schnell text-to-image model deployed by 302.ai | |
302ai-flux-realism-t2i | flux-realism text-to-image model deployed by 302.ai, enhanced with hyper-realistic LoRA | |
ideogram-v1-t2i | Official Ideogram V_1 text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
ideogram-v1-turbo-t2i | Official Ideogram V_1_turbo text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
ideogram-v2-t2i | Official Ideogram V_2 text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
ideogram-v2-turbo-t2i | Official Ideogram V_2_turbo text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
ideogram-v2a-t2i | Official Ideogram V_2A text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
ideogram-v2a-turbo-t2i | Official Ideogram V_2A_turbo text-to-image model | Supported aspect ratios: 1:1, 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:3, 3:1. Any other value will be treated as 1:1 |
recraft-v3-t2i | Official Recraft V3 text-to-image model | |
recraft-20b-t2i | Official Recraft 20B text-to-image model | |
luma-t2i | Official Luma text-to-image model | Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. Any other value will be treated as 1:1 |
luma-flash-t2i | Official Luma fast text-to-image model | Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. Any other value will be treated as 1:1 |
doubao-v2-t2i | Official Doubao v2.0 text-to-image model | Supported image dimensions are limited to [256, 768]; any other value will be treated as 512 |
doubao-v2-l-t2i | Official Doubao v2.0_L text-to-image model | Supported image dimensions are limited to [256, 768]; any other value will be treated as 512 |
doubao-v2.1-l-t2i | Official Doubao v2.1_L text-to-image model | Supported image dimensions are limited to [256, 768]; any other value will be treated as 512 |
doubao-v3-t2i | Official Doubao v3.0 text-to-image model | Supported image dimensions are limited to [256, 768]; any other value will be treated as 512 |
google-v3-t2i | Official Google Imagen-3 text-to-image model | Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. Any other value will be treated as 1:1 |
google-v3-fast-t2i | Official Google Imagen-3-fast text-to-image model | Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. Any other value will be treated as 1:1 |
minimaxi-t2i | Official Minimaxi minimaxi-image-01 text-to-image model | Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. Any other value will be treated as 1:1 |
cogview-4-t2i | Official Zhipu CogView-4 text-to-image model | Supported image sizes: 1024x1024, 768x1344, 864x1152, 1344x768, 1152x864, 1440x720, 720x1440. Any other value will be treated as 1024x1024 |
cogview-4-250304-t2i | Official Zhipu cogview-4-250304 text-to-image model | Supported image sizes: 1024x1024, 768x1344, 864x1152, 1344x768, 1152x864, 1440x720, 720x1440. Any other value will be treated as 1024x1024 |
baidu-irag-t2i | Baidu IRAG image generation model, which retrieves real images before generation to reduce hallucinations | |
hidream-i1-full-t2i | Zhixiang Future's i1-full text-to-image model | |
hidream-i1-dev-t2i | Zhixiang Future's i1-dev text-to-image model | |
hidream-i1-fast-t2i | Zhixiang Future's i1-fast text-to-image model |
Request
Header Params
Authorization
string
required
Example:
Bearer {{YOUR_API_KEY}}
Body Params application/json