All the models in one place
Run Z-Image Generator and every other model on Glif from one chat. One account, one balance, no API keys to wire up.
Z-Image Generator
Create images with custom styles, poses and outlines, with quality or speed modes.
Pricing details
- Turbo: 0.68–1.35 credits/MP. Quality: 1.35–1.62 credits/MP. Prompt expansion adds 0.34 credits per request.
Rated by blind team votes and an AI judge
As of
Score 18 · #13 of 14 in Product photography
90% range 12–27
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
On product photography: Wins 3 / Losses 16 / Ties 7 from 26 team votes, plus 5 AI judge scores.
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Other boards
Text-to-image: 17 · #14 of 14
Surgical image editing: 18 · #14 of 14
Image-to-image: Needs more ratings (5 of 20)
Character consistency: Needs more ratings (4 of 20)
Test outputs
Compare all modelsZ-Image Generator in practice
What it does and when to use it.
Model summary
Z Image generates images from text in quality or turbo mode. Turbo mode also supports image editing and ControlNet guidance for tasks such as following a pose or outline. Optional LoRA adapters guide style or subject. Cost depends on the megapixel count and selected mode.
Capabilities
Text to image
Image to image
Controlnet
Fast generation
Lora supported
Style adapters
Customization
Batch generation
Billed per megapixel
Suggested use cases
- Fast text-to-image generation
- High-throughput creative iteration and concepting
- Applying LoRA style adapters for custom aesthetics/subjects
- Rapid prototyping of visual ideas for products and marketing
- Batch generation workflows where speed/cost per megapixel matters