Pruna endpoints
pruna hosts serverless endpoints for your models in collaboration with the inference providers in the industry. These endpoints are optimized for speed, efficiency, and cost with Pruna. This makes them the fastest and most efficient way to run your models in production.
Performance models
What are performance models?
Performance models are Pruna’s own optimized models that we host and serve. We optimize them for the Pareto front of speed, cost, and quality. We optimize and offer as serverless well-known open source models for production use. Additionally, we have our own performance models like P-Image, P-Image-Edit, and P-Video. Get API access via the Pruna User Portal.
A performance text-to-image model delivering AI images in under one second, combining speed, quality, prompt adherence, and reliable text rendering.
A state-of-the-art image editing model, offering fast, high-quality multi-image editing with excellent prompt following and text rendering.
A performance video generation model delivering state-of-the-art AI video in seconds, with support for long-form generation, image references, and audio syncing.
P-Image LoRA and P-Image-Edit LoRA: Training and Inference (two workflows).
Get API access. Create an account and run inference via the Pruna User Portal.
API Reference for the performance models.
All models and pricing for our models.
Why performance models?
Pruna endpoints offer significant advantages over running your own model endpoints from scratch — thanks to our integrated optimizations and cloud infrastructure partnerships. Our performance models are optimized for the Pareto front of speed, cost, and quality. They provide:
Faster: Models are hosted and optimized for speed using the latest optimization algorithms.
Cheaper: Model optimizations reduce hardware requirements and reduce costs.
Better: Good optimizations can be lossless and those are our specialty.
Tip
Check out our benchmark comparison page for a head-to-head look at latency and price compared to self-hosting and other public endpoints. See how much time and money you can save.
General guides
Guides for overlapping topics:
Learn to identify and correct bias in AI-generated images using p-image and p-image-edit.
Generate with p-image, optionally refine with p-image-edit, then animate with p-video.
From lyrics to full music video with MiniMax Music 1.5, p-image, p-image-edit, and p-video.
Use an LLM to craft prompts, then build images, edits, and video segments.
Iteratively refine image prompts until the output matches your intent.
A guide for P-Image LoRA Training and Inference (p-image-trainer, p-image-lora).
A guide for P-Image-Edit LoRA Training and Inference (p-image-edit-trainer, p-image-edit-lora).
Prompting guides
Quick reference one-sheet guides for immediate use:
Get a quick overview of all the modalities and their overall prompt structure.
Learn all the nuances of image generation prompts.
Learn all the nuances of image editing prompts.
Learn all the nuances of video generation prompts.