GET
/v1/schemas/fal/image/fal-ai%2Fflux-general%2Fdifferential-diffusion
Accept:
Request body
36 properties · 3 required · 9 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The prompt to generate an image from. | |
| image_url* | string | URL of image to use as initial image. | |
| change_map_image_url* | string | URL of change map. | |
| use_beta_schedule | boolean | Specifies whether beta sigmas ought to be used. | default: false |
| controlnets | ControlNet[] | The controlnets to use for the image generation. Only one controlnet is supported at the moment. | default: [] |
| image_size | ImageSize | enum | The size of the generated image. | |
| nag_end | number | The proportion of steps to apply NAG. After the specified proportion of steps has been iterated, the remaining steps will use original attention processors in FLUX. | 0 < n ≤ 1 · default: 0.25 |
| use_cfg_zero | boolean | Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886. | default: false |
| reference_start | number | The percentage of the total timesteps when the reference guidance is to bestarted. | 0 ≤ n ≤ 1 · default: 0 |
| loras | LoraWeight[] | The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. | default: [] |
| fill_image | ImageFillInput | Use an image input to influence the generation. Can be used to fill images in masked areas. | nullable |
| max_shift | number | Max shift for the scheduled timesteps | 0.01 ≤ n ≤ 5 · default: 1.15 |
| num_images | integer | The number of images to generate. This is always set to 1 for streaming output. | 1 ≤ n ≤ 10 · default: 1 |
| base_shift | number | Base shift for the scheduled timesteps | 0.01 ≤ n ≤ 5 · default: 0.5 |
| guidance_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. | 0 ≤ n ≤ 20 · default: 3.5 |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. | default: true |
| nag_tau | number | The tau for NAG. Controls the normalization of the hidden state. Higher values will result in a less aggressive normalization, but may also lead to unexpected changes with respect to the original image. Not recommended to change this value. | n > 0 · default: 2.5 |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. | default: false |
| reference_strength | number | Strength of reference_only generation. Only used if a reference image is provided. | -3 ≤ n ≤ 3 · default: 0.65 |
| controlnet_unions | ControlNetUnion[] | The controlnet unions to use for the image generation. Only one controlnet is supported at the moment. | default: [] |
| reference_end | number | The percentage of the total timesteps when the reference guidance is to be ended. | 0 ≤ n ≤ 1 · default: 1 |
| real_cfg_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. | 0 ≤ n ≤ 5 · default: 3.5 |
| reference_image_url | string | URL of Image for Reference-Only | |
| output_format | enum | The format of the generated image. | jpeg | png · default: "png" |
| nag_alpha | number | The alpha value for NAG. This value is used as a final weighting factor for steering the normalized guidance (positive and negative prompts) in the direction of the positive prompt. Higher values will result in less steering on the normalized guidance where lo… | 0 < n ≤ 1 · default: 0.25 |
| use_real_cfg | boolean | Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true. If using XLabs IP-Adapter v1, this will be turned on!. | default: false |
| num_inference_steps | integer | The number of inference steps to perform. | 1 ≤ n ≤ 50 · default: 28 |
| control_loras | ControlLoraWeight[] | The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs and they will be merged together to generate the final image. | default: [] |
| easycontrols | EasyControlWeight[] | EasyControl Inputs to use for image generation. | default: [] |
| nag_scale | number | The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. | 1 < n ≤ 10 · default: 3 |
| negative_prompt | string | Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt. | default: "" |
| seed | integer | The same seed and the same prompt given to the same version of the model will output the same image every time. | nullable |
| scheduler | enum | Scheduler for the denoising process. | euler | dpmpp_2m · default: "euler" |
| sigma_schedule | const | Sigmas schedule for the denoising process. | "sgm_uniform" · nullable |
| strength | number | The strength to use for differential diffusion. 1.0 is completely remakes the image while 0.0 preserves the original. | 0.01 ≤ n ≤ 1 · default: 0.85 |
| ip_adapters | IPAdapter[] | IP-Adapter to use for image generation. | default: [] |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/flux-general/differential-diffusion","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}