Iris-Z-big on fal API

Iris-Z · Sperid Labs

Serverless
Open Weights

Last refreshed 2026-11-17. Next refresh: weekly.

Why use Iris-Z-big on fal API?

fal API offers Iris-Z-big. fal API is a developer platform for calling a large catalog of production-ready image, video, audio, vision, 3D, and multimodal generation models through a unified API surface.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: speridlabs/iris-z/text-to-image
Model ID
speridlabs/iris-z/text-to-image

Request example

Curated snippets for this provider are not sourced yet. Use fal API documentation with model ID speridlabs/iris-z/text-to-image.

Gotchas

  • Use provider model ID "speridlabs/iris-z/text-to-image", not the LLMReference slug "iris-z-big".

Capabilities

VisionMultimodal

About Iris-Z-big

Iris-Z-big is the larger of Sperid Labs' two Iris-Z models, announced November 11, 2026: a 32.2B-parameter image generator that produces appearance and geometry together. The same weights turn a prompt into an image, a prompt into an image with its depth, a photo into depth, and a depth map into an image, with no depth head and no second network; depth is encoded as an image in the same token sequence. Iris-Z builds on Black Forest Labs' FLUX.2. It runs at 512 and 1024 resolution and needs about 112 GB of GPU memory for all tasks.

Get Started

Model Specs

Released2026-11-11
Parameters32.2B
ArchitectureDiffusion Transformer

Related Models on fal API