Vidu Q2

Name: Vidu Q2
Brand: ShengShu Technology
Price: 0.1 USD
Availability: InStock

AI Image Editing Model

Image

ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing

Try Model

Supported Modes

Text to Image Image Edit

Active

Details

Model ID

vidu-q2

Creator

ShengShu Technology

Family

vidu

Max Input Images

Ready to integrate?

Access vidu-q2 via our unified API.

Create Account

Available at 1 provider

Starting from

$0.100 /image via fal.ai

Prices shown are in USD

Full pricing details

Providers & Pricing (2)

Vidu Q2 is available from 2 providers, with per-image pricing starting at $0.1 through fal.ai.

fal.ai

Text to Image

fal/vidu-q2

Provider Model ID: fal-ai/vidu/q2/text-to-image

$0.100 /image

View pricing details

fal.ai

Image Edit

fal/vidu-q2-edit

Provider Model ID: fal-ai/vidu/q2/reference-to-image

$0.100 /image

View pricing details

Vidu Q2 API OpenAI-compatible

Integrate Vidu Q2 into your workflow using Lumenfall's OpenAI-compatible API to perform advanced text-to-image generation and complex image editing through a single endpoint.

Base URL

https://api.lumenfall.ai/openai/v1

Model

vidu-q2

Code Examples

Text to Image

/v1/images/generations

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/generations \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "vidu-q2",

    "prompt": "",

    "size": "1024x1024"

}'

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.generate({

  model: 'vidu-q2',

  prompt: '',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.generate(

    model="vidu-q2",

    prompt="",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=vidu-q2" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'vidu-q2',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="vidu-q2",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for image generation	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") `1365x768` `768x1365` `1024x1024` WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") `9:16` `1:1` `16:9` Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `1K` Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

1K 3 sizes

Output	`size`		`aspect_ratio` + `resolution`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Gallery

View all 2 images

Vidu Q2 FAQ

How much does Vidu Q2 cost?

Vidu Q2 starts at $0.1 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use Vidu Q2 via API?

You can use Vidu Q2 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "vidu-q2". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Vidu Q2?

Vidu Q2 is available through fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

Vidu Q2 is a specialized image generation model developed by ShengShu Technology that prioritizes structural control and character consistency. Unlike standard text-to-image models that often struggle to maintain identity across multiple generations, Vidu Q2 is designed to process multiple reference images to anchor the visual features of a subject. This makes it a functional tool for creators who need to place the same character or object into varying environments and poses without losing visual fidelity.

Strengths

Character Consistency: The model excels at preserving the identity, facial features, and attire of a subject when provided with reference images, reducing the “hallucination” of new traits between frames or shots.
Multi-Reference Processing: It can ingest and synthesize information from more than one reference image simultaneously, allowing for better 360-degree understanding of a subject’s geometry and textures.
Structural Adherence: Vidu Q2 demonstrates high accuracy in following compositional instructions, ensuring that the spatial relationship between the subject and the background remains coherent.
Prompt Alignment: It maintains a strong correlation between complex text prompts and the resulting visual elements, even when constrained by specific image references.

Limitations

Style Rigidity: Because the model focuses heavily on consistency, it may sometimes inherit unwanted lighting or stylistic artifacts from the reference images, making it difficult to completely pivot to a drastically different art style without significant prompting effort.
Attribute Bleeding: When using multiple reference images with conflicting details (e.g., a character wearing different hats in two photos), the model may intermittently blend these features in unexpected ways.
Lower Creative Variance: Users seeking “happy accidents” or high stylistic diversity may find the model’s output overly constrained compared to more generalized diffusion models like Stable Diffusion XL or Flux.

Technical Background

Vidu Q2 is part of the Vidu family of generative models, utilizing a transformer-based architecture optimized for multimodal inputs. The model’s key technical differentiator is its specialized attention mechanism that gives weighted priority to visual tokens extracted from reference images. This training approach allows the model to treat reference images as “hard constraints” rather than mere stylistic suggestions, ensuring the generated output remains grounded in the provided visual data.

Best For

Vidu Q2 is best suited for storyboarding, character design, and brand-consistent marketing campaigns where maintaining a singular “hero” subject is critical. It is an effective choice for game developers and concept artists who need to visualize a character in multiple scenarios or lighting conditions.

Vidu Q2 is available to explore through the Lumenfall playground and can be integrated into production workflows via the Lumenfall unified API, providing a consistent interface for high-fidelity character generation.

Try Vidu Q2 in Playground

Generate images with custom prompts — no API key needed.

Open Playground