Model API

FLUX.1 [dev] with Controlnets and Loras

A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.

Model id

Use this in every request

flux-general/differential-diffusion

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-general/differential-diffusion",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light",
    "image_url": "https://example.com/input.png",
    "change_map_image_url": "https://example.com/input.png"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "flux-general/differential-diffusion", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light","image_url":"https://example.com/input.png","change_map_image_url":"https://example.com/input.png"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for flux-general/differential-diffusion
Name	Type	Description
`prompt`required	string	The prompt to generate an image from.
`image_size`	string (enum)	The size of the generated image. One of: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`
`num_inference_steps`	integer	The number of inference steps to perform. Default: `28`
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.
`loras`	array of objects	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.
`control_loras`	array of objects	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.
`controlnets`	array of objects	The controlnets to use for the image generation. Only one controlnet is supported at the moment.
`controlnet_unions`	array of objects	The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.
`ip_adapters`	array of objects	IP-Adapter to use for image generation.
`easycontrols`	array of objects	EasyControl Inputs to use for image generation.
`fill_image`	object	Use an image input to influence the generation. Can be used to fill images in masked areas.
`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. Default: `3.5`
`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. Default: `3.5`
`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`
`use_cfg_zero`	boolean	Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886. Default: `false`
`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`
`num_images`	integer	The number of images to generate. This is always set to 1 for streaming output. Default: `1`
`reference_image_url`	string (image URL)	URL of Image for Reference-Only
`reference_strength`	number	Strength of reference_only generation. Only used if a reference image is provided. Default: `0.65`
`reference_start`	number	The percentage of the total timesteps when the reference guidance is to bestarted. Default: `0`
`reference_end`	number	The percentage of the total timesteps when the reference guidance is to be ended. Default: `1`
`base_shift`	number	Base shift for the scheduled timesteps Default: `0.5`
`max_shift`	number	Max shift for the scheduled timesteps Default: `1.15`
`output_format`	string (enum)	The format of the generated image. Default: `png` One of: `jpeg`, `png`
`use_beta_schedule`	boolean	Specifies whether beta sigmas ought to be used. Default: `false`
`sigma_schedule`	string	Sigmas schedule for the denoising process.
`scheduler`	string (enum)	Scheduler for the denoising process. Default: `euler` One of: `euler`, `dpmpp_2m`
`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.
`nag_scale`	number	The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. Default: `3`
`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. Default: `2.5`
`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 lower values will result in considering the positive prompt guidance more. Default: `0.25`
`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. Default: `0.25`
`image_url`required	string (image URL)	URL of image to use as initial image.
`change_map_image_url`required	string (image URL)	URL of change map.
`strength`	number	The strength to use for differential diffusion. 1.0 is completely remakes the image while 0.0 preserves the original. Default: `0.85`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]

Pricing

up to$0.60/ run

The exact charge for your input comes from a quote. How charges settle