Photorealistic images
Uses the 14B model from Wan 2.2, which makes photorealistic images from text.
Create a picture from a description
Wan (V2.2 A14B)
Wan 2.2's 14B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail
Made by Alibaba250 creditsper run Pro
Opens the image studio with Wan (V2.2 A14B) ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Wan (V2.2 A14B) makes, what it needs and what you get
What it makes
Create a picture from a description
Turns a written description into a picture.
What you need
- A description of the picture
What you get
A new picture
About Wan (V2.2 A14B)
Wan (V2.2 A14B) uses the 14B model from Wan 2.2, made by Alibaba. It turns a text prompt into a photorealistic image, and you get an image file back.
You must provide a prompt. Everything else is optional. Image Size controls how large the picture is. Another option runs from 2 to 40, and a higher number improves quality but takes longer. Acceleration has two choices, none and regular. More acceleration makes generation faster at lower quality, and regular is the recommended level. Guidance Scale (1st Stage) and Guidance Scale (2nd Stage) each run from 1 to 10, and both control how closely the result follows your prompt. Enable Prompt Expansion and Enable Output Safety Checker are switches that are off until you turn them on.
Wan (V2.2 A14B) costs 250 credits. Wan Text to Image 5B uses the 5B model of Wan 2.2 instead of the 14B model, and its price is different.
Other models for this job
Same job: create a picture from a description. Compare before you choose.
Image Free Open
SDXL LightningCreate a picture from a description
A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.
ByteDance10 creditsper run
Image Free Open
Qwen Image LightningCreate a picture from a description
Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.
Alibaba10 creditsper run
Image Free Open
Qwen ImageCreate a picture from a description
Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.
Alibaba10 creditsper run
Image Free Open
Flux KreaCreate a picture from a description
A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.
Black Forest Labs85 creditsper run
What it does well
Two guidance settings
Guidance Scale (1st Stage) and Guidance Scale (2nd Stage) each run from 1 to 10. Both control how closely the result follows your prompt.
Acceleration choice
Pick none or regular. More acceleration is faster but lower in quality, and regular is the recommended level.
How to use Wan (V2.2 A14B)
How It Works
How It Works
01
Write your prompt
Describe the image you want in text. This is the only required input.
02
Tune the options
Set Image Size, Acceleration and the two guidance values. Turn on prompt expansion or the safety checker if you need either.
03
Generate
Run Wan (V2.2 A14B) for 250 credits and check the image file.
Tip Wan Text to Image 5B has a single Guidance Scale and an Image Format choice, which this model does not have.
Good for
Photo-style portraits
Describe a person in words and get a photorealistic image of them.
Realistic place pictures
Describe a room, a street or a landscape and get a photorealistic image of it.
Questions
Quick answers to help you get the most out of Wan (V2.2 A14B) in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. What can I change, and what does it cost?