Z Image Turbo ControlNet: Photoreal Image-to-Image with Depth & Pose Control on playground and API | RunComfy
tongyi-mai/z-image/turbo/controlnet/lora
The most powerful version of Z Image Turbo. Combine ControlNet (Canny, Depth, Pose) for structure locking with custom LoRAs for style transfer in a single high-speed workflow.
Table of contents
1. Get started
Use RunComfy's API to run tongyi-mai/z-image/turbo/controlnet/lora. For accepted inputs and outputs, see the model's schema.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/tongyi-mai/z-image/turbo/controlnet/lora \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "ultra-realistic interior rendering of a modern minimalist apartment living space with floor-to-ceiling glass windows on the right side, filling the room with soft natural daylight. A sleek light gray sectional sofa and a low rectangular coffee table with a matte finish sit on pale wood flooring. The walls are smooth and painted white, creating a clean and airy aesthetic. In the background, a green indoor plant adds a subtle touch of nature. The composition features high ceilings, long hallway perspective, and a serene, uncluttered atmosphere. Rendered in 8k, photorealistic, global illumination, unreal engine, architectural photography style, shot with a wide-angle lens, soft shadows, natural lighting.",
"image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7267/media-files/depth.jpg",
"loras": [
{
"path": "alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union",
"scale": 1
}
]
}'2. Authentication
Set the YOUR_API_TOKEN environment variable with your API key (manage keys in your Profile) and include it on every request as a Bearer token via the Authorization header: Authorization: Bearer $YOUR_API_TOKEN.
3. API reference
Submit a request
Submit an asynchronous generation job and immediately receive a request_id plus URLs to check status, fetch results, and cancel.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/tongyi-mai/z-image/turbo/controlnet/lora \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "ultra-realistic interior rendering of a modern minimalist apartment living space with floor-to-ceiling glass windows on the right side, filling the room with soft natural daylight. A sleek light gray sectional sofa and a low rectangular coffee table with a matte finish sit on pale wood flooring. The walls are smooth and painted white, creating a clean and airy aesthetic. In the background, a green indoor plant adds a subtle touch of nature. The composition features high ceilings, long hallway perspective, and a serene, uncluttered atmosphere. Rendered in 8k, photorealistic, global illumination, unreal engine, architectural photography style, shot with a wide-angle lens, soft shadows, natural lighting.",
"image_url": "https://playgrounds-storage-public.runcomfy.net/tools/7267/media-files/depth.jpg",
"loras": [
{
"path": "alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union",
"scale": 1
}
]
}'Monitor request status
Fetch the current state for a request_id ("in_queue", "in_progress", "completed", or "cancelled").
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
--header "Authorization: Bearer <token>"Retrieve request results
Retrieve the final outputs and metadata for the given request_id; if the job is not complete, the response returns the current state so you can continue polling.
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
--header "Authorization: Bearer <token>"Cancel a request
Cancel a queued job by request_id, in-progress jobs cannot be cancelled.
curl --request POST \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
--header "Authorization: Bearer <token>"4. File inputs
Hosted file (URL)
Provide a publicly reachable HTTPS URL. Ensure the host allows server‑side fetches (no login/cookies required) and isn't rate‑limited or blocking bots. Recommended limits: images ≤ 50 MB (~4K), videos ≤ 100 MB (~2–5 min @ 720p). Prefer stable or pre‑signed URLs for private assets.
5. Schema
Input schema
{
"type": "object",
"title": "Input",
"required": [
"prompt",
"image_url",
"loras"
],
"properties": {
"prompt": {
"title": "Prompt",
"description": "",
"type": "string",
"default": "ultra-realistic interior rendering of a modern minimalist apartment living space with floor-to-ceiling glass windows on the right side, filling the room with soft natural daylight. A sleek light gray sectional sofa and a low rectangular coffee table with a matte finish sit on pale wood flooring. The walls are smooth and painted white, creating a clean and airy aesthetic. In the background, a green indoor plant adds a subtle touch of nature. The composition features high ceilings, long hallway perspective, and a serene, uncluttered atmosphere. Rendered in 8k, photorealistic, global illumination, unreal engine, architectural photography style, shot with a wide-angle lens, soft shadows, natural lighting."
},
"image_url": {
"title": "Image",
"description": "URL of the input image used for ControlNet-based generation.",
"type": "string",
"default": "https://playgrounds-storage-public.runcomfy.net/tools/7267/media-files/depth.jpg"
},
"loras": {
"title": "LoRAs",
"description": "List of LoRAs to apply (maximum 3).",
"type": "array",
"default": [
{
"path": "alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union",
"scale": 1
}
],
"items": {
"path": {
"title": "LoRA Path",
"description": "URL, HuggingFace repo ID (owner/repo) to lora weights.",
"type": "string",
"format": "str",
"default": ""
},
"scale": {
"title": "LoRA Scale",
"description": "Scale of the LoRA model.",
"type": "float",
"format": "float_slider_with_range",
"minimum": 0,
"maximum": 4,
"default": 1
}
},
"maxItems": 3,
"minItems": 0
},
"image_size": {
"title": "Aspect Ratio (W:H)",
"description": "",
"type": "string",
"enum": [
"square_hd",
"square",
"portrait_4_3",
"portrait_16_9",
"landscape_4_3",
"landscape_16_9",
"auto"
],
"default": "auto"
},
"control_scale": {
"title": "Control Scale",
"description": "Controls how strongly the ControlNet conditions affect the output.",
"type": "float",
"default": 0.9,
"minimum": 0,
"maximum": 1
},
"control_start": {
"title": "Control Start",
"description": "Specifies the start point of the ControlNet conditioning during generation.",
"type": "float",
"default": 0,
"minimum": 0,
"maximum": 1
},
"control_end": {
"title": "Control End",
"description": "Specifies the end point of the ControlNet conditioning during generation.",
"type": "float",
"default": 0.4,
"minimum": 0,
"maximum": 1
},
"preprocess": {
"title": "Preprocess",
"description": "Defines what preprocessing (if any) will be applied to the ControlNet input image.",
"type": "string",
"enum": [
"none",
"canny",
"depth",
"pose"
],
"default": "none"
},
"num_inference_steps": {
"title": "Number of Inference Steps",
"description": "Specifies the number of inference steps during generation.",
"type": "integer",
"default": 8,
"minimum": 1,
"maximum": 8
},
"seed": {
"title": "Seed",
"description": "",
"type": "integer",
"default": 0
},
"enable_prompt_expansion": {
"title": "Magic Prompt",
"description": "Enables automatic prompt expansion to improve results; increases cost by 0.0025 credits per request.",
"type": "boolean",
"default": false
},
"output_format": {
"title": "Output Format",
"description": "Specifies the output image format.",
"type": "string",
"enum": [
"jpeg",
"png",
"webp"
],
"default": "png"
}
}
}Output schema
{
"output": {
"type": "object",
"properties": {
"image": {
"type": "string",
"format": "uri",
"description": "single image URL"
},
"video": {
"type": "string",
"format": "uri",
"description": "single video URL"
},
"images": {
"type": "array",
"description": "multiple image URLs",
"items": { "type": "string", "format": "uri" }
},
"videos": {
"type": "array",
"description": "multiple video URLs",
"items": { "type": "string", "format": "uri" }
}
}
}
}