# FLUX.1 [dev] with Controlnets and Loras API

> FLUX.1 [dev] text-to-image na may LoRAs, ControlNets, IP-Adapters, EasyControl at reference-image guidance

Gumagawa ng mga larawan mula sa `prompt` gamit ang iba’t ibang conditioning method: `loras`, `control_loras`, `controlnets`, `controlnet_unions`, `ip_adapters` at `easycontrols`, pati `fill_image` para sa mga naka-mask na bahagi. Tumatanggap din ito ng `reference_image_url`, negative prompt, at euler o dpmpp_2m scheduler. Hanggang 10 larawan bawat tawag, sa png o jpeg.

- Model id: `flux-general`
- Made by: Black Forest Labs
- Category: Text to Image
- Output: image
- Estimated price per run: $0.30 / image (cheapest run $0.30 (300 API credits))
- Run: `POST https://api.doitong.com/v1/run/flux-general`
- Quote: `POST https://api.doitong.com/v1/quote/flux-general`
- Docs page: https://doitong.com/fil/developers/models/flux-general

## Pricing

Price: **$0.30 / image**. Estimated from the typical cost of one run, per output (`num_images`). The quote is exactly what the run charges.

The full example input below costs $0.30 = 300 API credits (1 image × 300 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/flux-general` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt na gumagabay sa pagbuo ng larawan. |
| `image_size` |  | object {width, height} \| enum (string) | no |  | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Mga dimension ng nabuong larawan. |
| `num_inference_steps` |  | integer | no | `28` | 1 – 50 | Bilang ng inference step na isasagawa. |
| `seed` |  | integer \| null | no |  |  | Seed para sa nauulit na mga larawan: ang magkaparehong prompt at seed ay gumagawa ng magkaparehong larawan kapag hindi nagbago ang bersyon ng modelo. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | Mga LoRA na ang pinagsamang epekto ang bumubuo sa larawan, nang walang limitasyon sa bilang. |
| `loras[].path` |  | string | yes |  |  | Lokasyon ng LoRA weights, na tinutukoy bilang URL o path. |
| `loras[].scale` |  | object \| number | no | `1` |  | Pag-scale na inilalapat sa mga weight ng LoRA bago isama ang mga ito sa batayang modelo. Magbigay ng dictionary na nasa anyong {"layer_name":layer_scale} para itakda ang scale ng bawat layer; gumagamit ng 1.0 ang mga layer na hindi tinukoy. |
| `control_loras` |  | array of object {path, scale, control_image_url, preprocess} | no | `[]` |  | Mga control-image LoRA na pinagsama sa isang configuration para bumuo ng final na larawan; walang limitasyon ang bilang. |
| `control_loras[].path` |  | string | yes |  |  | Lokasyon ng LoRA weights, na tinutukoy bilang URL o path. |
| `control_loras[].scale` |  | object \| number | no | `1` |  | Pag-scale na inilalapat sa mga weight ng LoRA bago isama ang mga ito sa batayang modelo. Magbigay ng dictionary na nasa anyong {"layer_name":layer_scale} para itakda ang scale ng bawat layer; gumagamit ng 1.0 ang mga layer na hindi tinukoy. |
| `control_loras[].control_image_url` |  | string (image URL) | yes |  |  | URL ng larawang gagamitin bilang control na larawan. |
| `control_loras[].preprocess` |  | enum (string) | no | `None` | `canny`, `depth`, `None` | Preprocessing method na inilalapat sa ibinigay na larawan. |
| `controlnets` |  | array of object {path, config_url, variant, control_image_url, mask_image_url, mask_threshold, conditioning_scale, start_percentage, end_percentage} | no | `[]` |  | ControlNet configuration para sa pagbuo ng larawan, kasalukuyang hanggang isang ControlNet lamang. |
| `controlnets[].path` |  | string | yes |  |  | Lokasyon ng ControlNet weight, na tinukoy bilang URL o path. |
| `controlnets[].config_url` |  | string \| null | no |  |  | Opsyonal na URL patungo sa config.json file ng ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Opsyonal na variant para gamitin sa Hugging Face repository key. |
| `controlnets[].control_image_url` |  | string (image URL) | yes |  |  | URL ng larawang gagamitin bilang control na larawan. |
| `controlnets[].mask_image_url` |  | string (image URL) | no |  |  | URL ng mask na nauugnay sa control na larawan. |
| `controlnets[].mask_threshold` |  | number | no | `0.5` | 0.01 – 0.99 | Threshold value ng mask. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Pag-scale na inilalapat sa mga weight ng ControlNet bago isama ang mga ito sa batayang modelo. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Porsyento ng kabuuang timestep kung kailan magsisimulang makaapekto ang ControlNet sa pagbuo ng larawan. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Porsyento ng kabuuang timestep kung kailan titigil makaapekto ang ControlNet sa pagbuo ng larawan. |
| `controlnet_unions` |  | array of object {path, config_url, variant, controls} | no | `[]` |  | ControlNet union configuration para sa pagbuo ng larawan, na saklaw ng kasalukuyang limitasyon na isang ControlNet lamang. |
| `controlnet_unions[].path` |  | string | yes |  |  | Lokasyon ng ControlNet weight, na tinukoy bilang URL o path. |
| `controlnet_unions[].config_url` |  | string \| null | no |  |  | Opsyonal na URL patungo sa config.json file ng ControlNet. |
| `controlnet_unions[].variant` |  | string \| null | no |  |  | Opsyonal na variant para gamitin sa Hugging Face repository key. |
| `controlnet_unions[].controls` |  | array of object {control_image_url, mask_image_url, control_mode, conditioning_scale, mask_threshold, start_percentage, end_percentage} | yes |  |  | Mga control na larawan at kaugnay na mode na ibinibigay sa ControlNet. |
| `controlnet_unions[].controls[].control_image_url` |  | string (image URL) | yes |  |  | URL ng larawang gagamitin bilang control na larawan. |
| `controlnet_unions[].controls[].mask_image_url` |  | string (image URL) | no |  |  | URL ng mask na nauugnay sa control na larawan. |
| `controlnet_unions[].controls[].control_mode` |  | enum (string) | yes |  | `canny`, `tile`, `depth`, `blur`, `pose`, `gray`, `low-quality` | Control mode na ginagamit ng Flux Controlnet Union. Mga opsyon: ginagabayan ng canny ang pagbuo gamit ang edges; ginagabayan ito ng tile gamit ang tiles; depth gamit ang grayscale depth map; bina-blur ng blur ang larawan; ginagabayan ng pose ang pagbuo gamit ang pose ng larawan; ginagawang grayscale ng gray ang larawan; gumagawa ang low-quality ng mababang kalidad na bersyon ng larawan. |
| `controlnet_unions[].controls[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Pag-scale na inilalapat sa mga weight ng ControlNet bago isama ang mga ito sa batayang modelo. |
| `controlnet_unions[].controls[].mask_threshold` |  | number | no | `0.5` | 0.01 – 0.99 | Threshold value ng mask. |
| `controlnet_unions[].controls[].start_percentage` |  | number | no | `0` | 0 – 1 | Porsyento ng kabuuang timestep kung kailan magsisimulang makaapekto ang ControlNet sa pagbuo ng larawan. |
| `controlnet_unions[].controls[].end_percentage` |  | number | no | `1` | 0 – 1 | Porsyento ng kabuuang timestep kung kailan titigil makaapekto ang ControlNet sa pagbuo ng larawan. |
| `ip_adapters` |  | array of object {path, subfolder, weight_name, image_encoder_path, image_encoder_subfolder, image_encoder_weight_name, image_url, mask_image_url, mask_threshold, scale} | no | `[]` |  | IP-Adapter na ginagamit habang bumubuo ng larawan. |
| `ip_adapters[].path` |  | string | yes |  |  | Lokasyon ng IP-Adapter sa Hugging Face. |
| `ip_adapters[].subfolder` |  | string \| null | no |  |  | Subfolder na naglalaman ng ip_adapter weight. |
| `ip_adapters[].weight_name` |  | string \| null | no |  |  | Safetensors filename para sa weight ng IP-Adapter. |
| `ip_adapters[].image_encoder_path` |  | string | yes |  |  | Lokasyon ng encoder ng larawan para sa IP-Adapter, gaya ng 'openai/clip-vit-large-patch14'. |
| `ip_adapters[].image_encoder_subfolder` |  | string \| null | no |  |  | Subfolder na naglalaman ng mga weight para sa encoder ng larawan. |
| `ip_adapters[].image_encoder_weight_name` |  | string \| null | no |  |  | Pangalan ng encoder ng larawan. |
| `ip_adapters[].image_url` |  | string (image URL) | yes |  |  | URL ng larawang ginagamit bilang kondisyon at ibinibigay sa IP-Adapter. |
| `ip_adapters[].mask_image_url` |  | string (image URL) \| null | no |  |  | URL ng mask na nauugnay sa control na larawan. |
| `ip_adapters[].mask_threshold` |  | number | no | `0.5` | 0.01 – 0.99 | Threshold value ng mask. |
| `ip_adapters[].scale` |  | number | yes |  |  | Scaling factor ng IP-Adapter. |
| `easycontrols` |  | array of object {control_method_url, scale, image_url, image_control_type} | no | `[]` |  | Mga EasyControl input na ginagamit habang bumubuo ng larawan. |
| `easycontrols[].control_method_url` |  | string | yes |  |  | Safetensor weight URL ng control method, o suportadong identifier: `canny`, `depth`, `hedsketch`, `inpainting`, `pose`, `seg`, `subject`, `ghibli`. |
| `easycontrols[].scale` |  | number | no | `1` | 0 – 2 | Scaling factor ng control method. |
| `easycontrols[].image_url` |  | string (image URL) | yes |  |  | URL ng larawang gagamitin bilang control input. |
| `easycontrols[].image_control_type` |  | enum (string) | yes |  | `subject`, `spatial` | Mode ng pagkontrol gamit ang larawan; tumatanggap ng `spatial` o `subject`. |
| `fill_image` |  | object {fill_image_url} \| null | no |  |  | Input na larawan na gumagabay sa pagbuo at maaaring magbigay ng content para sa mga masked region. |
| `fill_image.fill_image_url` |  | string (image URL) \| array of image URL | no | `[]` |  | Mga URL ng larawan para sa pagpuno gamit ang redux prompting. |
| `guidance_scale` |  | number | no | `3.5` | 0 – 20 | Lakas ng pagsunod sa prompt para sa pagpili ng larawan, na ipinapahayag bilang CFG (Classifier Free Guidance). |
| `real_cfg_scale` |  | number | no | `3.5` | 0 – 5 | Lakas ng pagsunod sa prompt para sa pagpili ng larawan, na ipinapahayag bilang CFG (Classifier Free Guidance). |
| `use_real_cfg` |  | boolean | no | `false` |  | Classical CFG switch, awtomatikong naka-enable sa XLabs IP-Adapter v1. Katulad ng mga modelong gaya ng SD1.5 at SDXL ang behavior ng guidance. |
| `use_cfg_zero` |  | boolean | no | `false` |  | Pinapagana ang CFG-zero initialization sampling, na inilalarawan sa https://arxiv.org/abs/2503.18886. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 10 | Itakda kung ilang larawan ang bubuuin; nakapirmi sa 1 ang pagpipiliang ito kapag naka-stream ang output. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Safety checking na nagbabalik ng mga itim na larawan kapalit ng mga larawang na-flag na unsafe. Pinapagana ng true ang checking; dini-disable ito ng false para lamang sa mga awtorisadong account, habang sinusuri pa rin ang mga kahilingang walang authorization. |
| `reference_image_url` |  | string (image URL) | no |  |  | URL ng larawang ginagamit para sa paggabay ng Reference-Only. |
| `reference_strength` |  | number | no | `0.65` | -3 – 3 | Impluwensiya ng reperensiyang larawan habang bumubuo gamit ang reference_only; walang epekto ang setting ng lakas na ito kung walang ibinigay na reperensiyang larawan. |
| `reference_start` |  | number | no | `0` | 0 – 1 | Panimulang punto ng reference guidance, na ipinapahayag bilang porsyento ng lahat ng timestep. |
| `reference_end` |  | number | no | `1` | 0 – 1 | Pangwakas na punto ng reference guidance, na ipinapahayag bilang porsyento ng lahat ng timestep. |
| `base_shift` |  | number | no | `0.5` | 0.01 – 5 | Baseline shift na inilalapat sa mga naka-schedule na timestep. |
| `max_shift` |  | number | no | `1.15` | 0.01 – 5 | Maximum shift na inilalapat sa mga naka-schedule na timestep. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png` | File format ng resultang larawan. |
| `use_beta_schedule` |  | boolean | no | `false` |  | Kinokontrol kung gagamit ng beta sigma. |
| `sigma_schedule` |  | string \| null | no |  |  | Sigma schedule na ginagamit habang nagde-denoise. |
| `scheduler` |  | enum (string) | no | `euler` | `euler`, `dpmpp_2m` | Scheduler na ginagamit habang nagde-denoise. |
| `negative_prompt` |  | string | no | `` |  | Negative prompt na default na pinoproseso gamit ang NAG upang bawasan ang tinukoy na hindi kanais-nais na feature sa mga binubuong larawan. |
| `nag_scale` |  | number | no | `3` | ≤ 10, > 1 | Pag-iwas sa negative prompt na kinokontrol ng NAG scale: kapag tinaasan ito, mas hindi magiging katulad ng negative description ang binubuong larawan. |
| `nag_tau` |  | number | no | `2.5` | > 0 | NAG tau setting para sa hidden-state normalization; inirerekomendang huwag itong baguhin. Pinahihina ng pagtataas nito ang normalization at maaaring magdulot ng hindi inaasahang paglayo sa orihinal na larawan. |
| `nag_alpha` |  | number | no | `0.25` | ≤ 1, > 0 | Itinatakda ng NAG alpha kung gaano kalaki ang pag-redirect ng positive prompt sa normalized guidance na pinagsasama ang positive at negative prompt. Nagbibigay ang huling weighting na ito ng mas malaking impluwensya sa positive prompt sa mababang setting at binabawasan ang pag-redirect sa mataas na setting. |
| `nag_end` |  | number | no | `0.25` | ≤ 1, > 0 | NAG cutoff na ipinapahayag bilang proporsyon ng mga step ng pagbuo. Pagkatapos tumakbo ang NAG sa paunang proporsyong ito, papalit ang orihinal na attention processor ng FLUX. |

File parameters (`reference_image_url`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/flux-general?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/flux-general?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/flux-general", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "flux-general",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "flux-general",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "width": 1024,
        "height": 768,
        "content_type": "image/jpeg"
      }
    ],
    "timings": {},
    "seed": 42,
    "has_nsfw_concepts": [
      false
    ],
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `images` | array of object {url, width, height, content_type} | Impormasyon ng file para sa mga nabuong larawan. |
| `timings` | object |  |
| `seed` | integer | Seed para sa pagbuo ng larawan, kasama ang random na napiling value kung walang seed sa input; kung hindi, inuulit nito ang ibinigay na value. |
| `has_nsfw_concepts` | array of boolean | Nagsasaad kung may mga konseptong NSFW sa nabuong mga larawan. |
| `prompt` | string | Prompt na ginagamit sa pagbuo ng larawan. |

## Related models

- [FLUX.1 \[dev\] with Controlnets and Loras · Differential Diffusion](https://doitong.com/developers/models/flux-general/differential-diffusion.md) (`flux-general/differential-diffusion`): $0.138 / image
- [FLUX.1 \[dev\] with Controlnets and Loras · Image to Image](https://doitong.com/developers/models/flux-general/image-to-image.md) (`flux-general/image-to-image`): $0.15 / image
- [FLUX.1 \[dev\] with Controlnets and Loras · Inpainting](https://doitong.com/developers/models/flux-general/inpainting.md) (`flux-general/inpainting`): $0.192 / image
- [FLUX.1 \[dev\] with Controlnets and Loras · Rf Inversion](https://doitong.com/developers/models/flux-general/rf-inversion.md) (`flux-general/rf-inversion`): $0.025 / image
- [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md) (`flux/dev`): $0.025 / megapixel
- [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md) (`flux/schnell`): $0.003 / megapixel
- [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md) (`flux-2`): $0.012 / megapixel
- [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md) (`flux-2-pro`): $0.015 / megapixel of output image

## Links

- HTML page: https://doitong.com/developers/models/flux-general
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=flux-general
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/flux-general