Iris-Z
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
Custom Resolution
Depth ensemble members
Default
1
$0.01 per member; the aligned predictions form one result.
Depth estimation steps
Default
4
Depth working/output resolution
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
Default
png
Options (2)
png, jpeg
Generation guidance
Default
3.5
Generation steps
Default
50
Input depth format
Default
colorized
Options (3)
Iris-Z colored depth, Grayscale: bright is far, Grayscale: bright is near
Mode
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…