FLUX 2 Lora Gallery Realism
Usage-based pricing
ae_flux_2_lora_gallery_realism
Create photorealistic images from text prompts with natural lighting and authentic detail.
Usage-based pricing
Pricing
The charge per call is (max(25.2 × total generated image area (megapixels), 0)) AE credits. All applicable conditions are combined to calculate the total.
Charges are based on the total generated image area; the size and number of generated images affect this usage.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.seed | integer | unknown | No | Random seed for reproducibility. Same seed with same prompt will produce same result. | — |
request_body.prompt | string | Yes | The prompt to generate a realistic image with natural lighting and authentic details. | — |
request_body.sync_mode | boolean | No | If `True`, the media will be returned as a data URI and won't be saved in history. | false |
request_body.image_size | object | string | No | The size of the generated image. | landscape_4_3 |
request_body.image_size.width | integer | No | The width of the generated image. | 512 |
request_body.image_size.height | integer | No | The height of the generated image. | 512 |
request_body.lora_scale | number | No | The strength of the realism effect. | 1 |
request_body.num_images | integer | No | Number of images to generate | 1 |
request_body.acceleration | enum (none | regular) | No | Acceleration level for image generation. 'regular' balances speed and quality. | regular |
request_body.output_format | enum (png | jpeg | webp) | No | The format of the output image | png |
request_body.guidance_scale | number | No | The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. | 2.5 |
request_body.num_inference_steps | integer | No | The number of inference steps to perform. | 40 |
request_body.enable_safety_checker | boolean | No | Whether to enable the safety checker for the generated image. | true |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeySubmit first, then query with the returned task_id until the task completes.
Request coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_flux_2_lora_gallery_realism' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"enable_safety_checker": false,
"guidance_scale": 3.5,
"image_size": "landscape_16_9",
"lora_scale": 1,
"num_inference_steps": 40,
"output_format": "jpeg",
"prompt": "Aerial bird'\''s-eye view from high above of a complete pet-themed architectural complex at Moshui Lake Park in Wuhan, China. The entire U-shaped siheyuan courtyard layout is fully visible from a top-down panoramic angle, all buildings clearly shown with no occlusion. The complex consists of modular container-style wooden cabins with white walls and warm wood accents, modern trendy pop-up store style. Arranged in a U shape around the central grass courtyard lawn are all functional zones: a coffee shop, market stalls, a pet training school, a comprehensive service center with a rooftop swimming pool, a small-dog swimming pool, a pet health management building, a pet hotel boarding area, and a glass-walled live pet display and live-streaming zone. In the distant background are the Yellow Crane Tower and the Yangtze River Bridge of Wuhan, with cherry blossom trees scattered around. Photorealistic architectural rendering, natural daylight, realistic materials, 16:9 wide horizontal composition, every building of the entire complex clearly visible and well-arranged across the wide frame.",
"sync_mode": false
}
}
}'Response exampleresponse.json
{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "6ebe7b68-5911-4a52-9df8-c71ef11396e8"
}This example shows part of the response. Copied content is valid JSON.
Guides using this tool
See how this tool fits into real workflows
Anime & Illustration Generation with AI AgentsLet an AI agent generate anime-style characters and scenes from one plain-English prompt — compare multiple models, render text on posters, keep a character consistent, and batch out a full illustration set without leaving your editor.Character-Consistent Image Generation with AI AgentsLock a character's look with a reference image and have an AI agent keep the same person consistent across scenes and poses — batch out IP, picture-book, comic and mascot image sets from one instruction.

