Image

FLUX.1 General (I2I)

Credit-based pricing. Supports reference images, batch up to 4.

Try FLUX.1 General (I2I) →Compare models

Output

image

Aspect ratio

1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21, Custom

Resolution

512, 1024, 2048

Max batch

Inputs

Reference image (required)

Batch up to 4 per request

Example prompt

Transform into a vivid Art Nouveau illustration, curling organic foliage borders, jewel-tone stained-glass palette, stylized mountains and river rendered as flowing botanical ornaments, decorative gold leaf accents

Try this prompt →

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/flux-general/image-to-image.

POST/api/v1/generate45 fields · 3 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`prompt`	string	Required	Optional model input.
`lora_path`	string	Optional	URL or path to the first LoRA weights. · Default:
`lora_scale`	number	Optional	Blend strength for LoRA 1 (0 = off, 1 = full). · Default: 1 · Range: -4–4
`lora_path_2`	string	Optional	URL or path to the second LoRA weights. · Default:
`lora_scale_2`	number	Optional	Blend strength for LoRA 2. · Default: 1 · Range: -4–4
`lora_path_3`	string	Optional	URL or path to the third LoRA weights. · Default:
`lora_scale_3`	number	Optional	Blend strength for LoRA 3. · Default: 1 · Range: -4–4
`strength`	number	Optional	The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the · Default: 0.85 · Range: 0.01–1
`output_format`	string	Optional	The format of the generated image. · Allowed: jpeg, png · Default: png
`base_shift`	number	Optional	Base shift for the scheduled timesteps · Default: 0.5 · Range: 0.01–5
`sigma_schedule`	string	Optional	Sigmas schedule for the denoising process. · Allowed: sgm_uniform
`reference_end`	number	Optional	The percentage of the total timesteps when the reference guidance is to be ended. · Default: 1 · Range: 0–1
`real_cfg_scale`	number	Optional	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 · Default: 3.5 · Range: 0–5
`nag_end`	number	Optional	The proportion of steps to apply NAG. After the specified proportion of steps has been iterated, the remaining steps will use original attention proce · Default: 0.25 · Range: …–1
`seed`	integer	Optional	The same seed and the same prompt given to the same version of the model will output the same image every time.
`reference_strength`	number	Optional	Strength of reference_only generation. Only used if a reference image is provided. · Default: 0.65 · Range: -3–3
`use_beta_schedule`	boolean	Optional	Specifies whether beta sigmas ought to be used. · Default: false
`negative_prompt`	string	Optional	Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt. · Default:
`reference_start`	number	Optional	The percentage of the total timesteps when the reference guidance is to bestarted. · Default: 0 · Range: 0–1
`nag_tau`	number	Optional	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 un · Default: 2.5
`max_shift`	number	Optional	Max shift for the scheduled timesteps · Default: 1.15 · Range: 0.01–5
`guidance_scale`	number	Optional	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 · Default: 3.5 · Range: 0–20
`reference_image_url`	string	Required	URL of Image for Reference-Only
`scheduler`	string	Optional	Scheduler for the denoising process. · Allowed: euler, dpmpp_2m · Default: euler
`nag_alpha`	number	Optional	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 di · Default: 0.25 · Range: …–1
`use_cfg_zero`	boolean	Optional	Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886. · Default: false
`use_real_cfg`	boolean	Optional	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 · Default: false
`nag_scale`	number	Optional	The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. · Default: 3 · Range: …–10
`enable_safety_checker`	boolean	Optional	If set to true, the safety checker will be enabled. · Default: true
`num_inference_steps`	number	Optional	The number of inference steps to perform. · Default: 28 · Range: 1–50
`fill_image`	string	Optional	URL of an image used to fill masked areas / influence the generation.
`controlnets`	object	Optional	JSON array of ControlNet configs, e.g. [{"path":"...","control_image_url":"...","conditioning_scale":1}]. Only one controlnet is supported at this time.
`controlnet_unions`	object	Optional	JSON array of ControlNet Union configs, e.g. [{"path":"...","controls":[...]}].
`ip_adapters`	object	Optional	JSON array of IP-Adapter configs, e.g. [{"path":"...","image_encoder_path":"...","image_url":"...","scale":1}].
`control_loras`	object	Optional	JSON array of control-image LoRAs, e.g. [{"path":"...","control_image_url":"...","scale":1,"preprocess":"canny"}].
`easycontrols`	object	Optional	JSON array of EasyControl inputs, e.g. [{"control_method_url":"...","image_url":"...","image_control_type":"...","scale":1}].
`aspect_ratio`	string	Optional	Allowed: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21, Custom
`resolution`	string	Optional	Allowed: 512, 1024, 2048
`num_images`	integer	Optional	Range: 1–4

Minimal request example

{
  "model_id": "fal-ai/flux-general/image-to-image",
  "prompt": "Transform into a vivid Art Nouveau illustration, curling organic foliage borders, jewel-tone stained-glass palette, stylized mountains and river rendered as flowing botanical ornaments, decorative gold leaf accents",
  "reference_image_url": "your_reference_image_url"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fflux-general%2Fimage-to-image",
  "title": "FLUX.1 General (I2I) generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/flux-general/image-to-image.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/flux-general/image-to-image",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "lora_path": {
      "title": "LoRA 1",
      "description": "URL or path to the first LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale": {
      "title": "LoRA 1 Scale",
      "description": "Blend strength for LoRA 1 (0 = off, 1 = full).",
      "default": 1,
      "type": "number",
      "minimum": -4,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_2": {
      "title": "LoRA 2",
      "description": "URL or path to the second LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale_2": {
      "title": "LoRA 2 Scale",
      "description": "Blend strength for LoRA 2.",
      "default": 1,
      "type": "number",
      "minimum": -4,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_3": {
      "title": "LoRA 3",
      "description": "URL or path to the third LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale_3": {
      "title": "LoRA 3 Scale",
      "description": "Blend strength for LoRA 3.",
      "default": 1,
      "type": "number",
      "minimum": -4,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "strength": {
      "title": "Strength",
      "description": "The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the",
      "default": 0.85,
      "type": "number",
      "minimum": 0.01,
      "maximum": 1
    },
    "output_format": {
      "title": "Output Format",
      "description": "The format of the generated image.",
      "default": "png",
      "type": "string",
      "enum": [
        "jpeg",
        "png"
      ]
    },
    "base_shift": {
      "title": "Base Shift",
      "description": "Base shift for the scheduled timesteps",
      "default": 0.5,
      "type": "number",
      "minimum": 0.01,
      "maximum": 5
    },
    "sigma_schedule": {
      "title": "Sigma Schedule",
      "description": "Sigmas schedule for the denoising process.",
      "type": "string",
      "enum": [
        "sgm_uniform"
      ]
    },
    "reference_end": {
      "title": "Reference End",
      "description": "The percentage of the total timesteps when the reference guidance is to be ended.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "real_cfg_scale": {
      "title": "Real Cfg Scale",
      "description": "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",
      "default": 3.5,
      "type": "number",
      "minimum": 0,
      "maximum": 5
    },
    "nag_end": {
      "title": "Nag End",
      "description": "The proportion of steps to apply NAG. After the specified proportion of steps has been iterated, the remaining steps will use original attention proce",
      "default": 0.25,
      "type": "number",
      "maximum": 1
    },
    "seed": {
      "title": "Seed",
      "description": "The same seed and the same prompt given to the same version of the model will output the same image every time.",
      "type": "integer"
    },
    "reference_strength": {
      "title": "Reference Strength",
      "description": "Strength of reference_only generation. Only used if a reference image is provided.",
      "default": 0.65,
      "type": "number",
      "minimum": -3,
      "maximum": 3
    },
    "use_beta_schedule": {
      "title": "Use Beta Schedule",
      "description": "Specifies whether beta sigmas ought to be used.",
      "default": false,
      "type": "boolean"
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "description": "Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt.",
      "default": "",
      "type": "string"
    },
    "reference_start": {
      "title": "Reference Start",
      "description": "The percentage of the total timesteps when the reference guidance is to bestarted.",
      "default": 0,
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "nag_tau": {
      "title": "Nag Tau",
      "description": "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 un",
      "default": 2.5,
      "type": "number"
    },
    "max_shift": {
      "title": "Max Shift",
      "description": "Max shift for the scheduled timesteps",
      "default": 1.15,
      "type": "number",
      "minimum": 0.01,
      "maximum": 5
    },
    "guidance_scale": {
      "title": "Guidance Scale",
      "description": "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",
      "default": 3.5,
      "type": "number",
      "minimum": 0,
      "maximum": 20
    },
    "reference_image_url": {
      "title": "Reference Image Url",
      "description": "URL of Image for Reference-Only",
      "type": "string"
    },
    "scheduler": {
      "title": "Scheduler",
      "description": "Scheduler for the denoising process.",
      "default": "euler",
      "type": "string",
      "enum": [
        "euler",
        "dpmpp_2m"
      ]
    },
    "nag_alpha": {
      "title": "Nag Alpha",
      "description": "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 di",
      "default": 0.25,
      "type": "number",
      "maximum": 1
    },
    "use_cfg_zero": {
      "title": "Use Cfg Zero",
      "description": "Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.",
      "default": false,
      "type": "boolean"
    },
    "use_real_cfg": {
      "title": "Use Real Cfg",
      "description": "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",
      "default": false,
      "type": "boolean"
    },
    "nag_scale": {
      "title": "Nag Scale",
      "description": "The scale for NAG. Higher values will result in a image that is more distant to the negative prompt.",
      "default": 3,
      "type": "number",
      "maximum": 10
    },
    "enable_safety_checker": {
      "title": "Enable Safety Checker",
      "description": "If set to true, the safety checker will be enabled.",
      "default": true,
      "type": "boolean"
    },
    "num_inference_steps": {
      "title": "Num Inference Steps",
      "description": "The number of inference steps to perform.",
      "default": 28,
      "type": "number",
      "minimum": 1,
      "maximum": 50,
      "multipleOf": 1
    },
    "fill_image": {
      "title": "Fill Image URL",
      "description": "URL of an image used to fill masked areas / influence the generation.",
      "type": "string"
    },
    "controlnets": {
      "title": "ControlNets (JSON)",
      "description": "JSON array of ControlNet configs, e.g. [{\"path\":\"...\",\"control_image_url\":\"...\",\"conditioning_scale\":1}]. Only one controlnet is supported at this time.",
      "type": "object",
      "additionalProperties": true
    },
    "controlnet_unions": {
      "title": "ControlNet Unions (JSON)",
      "description": "JSON array of ControlNet Union configs, e.g. [{\"path\":\"...\",\"controls\":[...]}].",
      "type": "object",
      "additionalProperties": true
    },
    "ip_adapters": {
      "title": "IP-Adapters (JSON)",
      "description": "JSON array of IP-Adapter configs, e.g. [{\"path\":\"...\",\"image_encoder_path\":\"...\",\"image_url\":\"...\",\"scale\":1}].",
      "type": "object",
      "additionalProperties": true
    },
    "control_loras": {
      "title": "Control LoRAs (JSON)",
      "description": "JSON array of control-image LoRAs, e.g. [{\"path\":\"...\",\"control_image_url\":\"...\",\"scale\":1,\"preprocess\":\"canny\"}].",
      "type": "object",
      "additionalProperties": true
    },
    "easycontrols": {
      "title": "EasyControls (JSON)",
      "description": "JSON array of EasyControl inputs, e.g. [{\"control_method_url\":\"...\",\"image_url\":\"...\",\"image_control_type\":\"...\",\"scale\":1}].",
      "type": "object",
      "additionalProperties": true
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "1:1",
        "16:9",
        "9:16",
        "4:3",
        "3:4",
        "21:9",
        "9:21",
        "Custom"
      ]
    },
    "resolution": {
      "type": "string",
      "enum": [
        "512",
        "1024",
        "2048"
      ]
    },
    "num_images": {
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    }
  },
  "required": [
    "model_id",
    "prompt",
    "reference_image_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does FLUX.1 General (I2I) cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if FLUX.1 General (I2I) fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call FLUX.1 General (I2I) from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/flux-general/image-to-image". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with FLUX.1 General (I2I)?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.