Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Image
  3. Speridlabs

Iris-Z

Try Model

Iris-Z is a FLUX.2-based joint RGB and depth model. Generate an image from text, create RGB with a matching depth visualization and float32 log-depth array, estimate depth from one image, or generate from a square depth map. Text generation supports up to 1,310,720 pixels with 16-pixel increments. Depth-guided output is square at 512 or 1024 pixels. Prompts are limited to 4096 characters and truncated to 512 encoder tokens.

Added Nov 17, 2026

Details

Approx. Price
$0.100 per image
Model type
both

Settings

Generation controls available for this model.

Images Per Run

Fixed 1

Output images

Input Images

Up to 1

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square

Custom Resolution

Depth ensemble members

Number

Default

1

$0.01 per member; the aligned predictions form one result.

Depth estimation steps

Number

Default

4

Depth working/output resolution

Select

Default

1024

Options (3)

auto, 512, 1024

Depth estimation returns the original input dimensions; auto selects its working size. Depth-guided output requires 512 or 1024 and a square input.

Generated image format

Select

Default

png

Options (2)

png, jpeg

Generation guidance

Number

Default

3.5

Generation steps

Number

Default

50

Input depth format

Select

Default

colorized

Options (3)

Iris-Z colored depth, Grayscale: bright is far, Grayscale: bright is near

Mode

Select

Default

auto

Options (5)

Text to image / uploaded depth to image, Text to image, Text to RGB + depth, Square depth map to image +1 more

Showing 9 of 12 settings.

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related image models

Compare Iris-Z with similar models from the same provider or model family.

Iris-Z Small

speridlabs/iris-z/small

Iris-Z Small is the smaller variant of the FLUX.2-based joint RGB and depth model. Generate an image from text, create RGB with a matching depth visualization and float32 log-depth array, estimate depth from one image, or generate from a square depth map. Text generation supports up to 1,310,720 pixels with 16-pixel increments. Depth-guided output is square at 512 or 1024 pixels. Prompts are limited to 4096 characters and truncated to 512 encoder tokens.

BRIA RMBG-3.0

bria/rmbg-3

Remove the background from one image and return a transparent PNG at the original dimensions. Built on Fibo 2.0 and trained on licensed data, BRIA RMBG-3.0 is designed to preserve product text, logos, fine hair and openwork details. Transparent objects and low-contrast boundaries can be difficult. No prompt is required.

MiniMax H3 Image

minimax-h3-image

MiniMax H3 Image generates images from text and combines and edits up to 16 reference images with text instructions. Create scenes, characters, product concepts and illustrations at 1K or 2K, choose from fifteen aspect ratios, and save one PNG, JPEG or WebP image per request. Reference images must be PNG, JPEG or WebP, with each side between 128 and 8192 pixels and an aspect ratio no greater than 4:1. Edits cost $0.04 with one reference, plus $0.008 for each additional reference (up to 16 total).

Seedream 5.5

bytedance/seedream-v5.5

Seedream 5.5 by ByteDance generates images from text and edits images with up to 10 ordered references. Choose from fifteen aspect ratios and 1K, 1.5K or 2K output. Save as PNG or JPEG, with transparent backgrounds available in PNG.

Seedream 5.5 Layer Decomposition

bytedance/seedream-v5.5/layer-decomposition

Separate one image into a base image followed by transparent PNG layers. Add an optional prompt to guide the split, choose 1K, 1.5K or 2K, and set a limit of 2 to 100 images including the base. The charge uses the selected limit even when fewer images are returned. The base can be PNG or JPEG.

GPT Image 2.6 Flare

gpt-image-2.6-flare

GPT Image 2.6 Flare generates images from text and edits images with up to 16 references. Designed for fast iteration. Choose low, medium, or high complexity independently of five quality levels, with 1K, 2K, or 4K output and 15 aspect ratios. Custom pixel sizes are also supported through the API. Supports PNG, JPEG, WebP, transparent PNG/WebP backgrounds, and transparent PNG markup annotations for regional edits through the API. Also generates animated GIFs from a prompt or from reference images. Prices are estimated before generation and settled from actual token usage.