Image generation

Pendra generates images from text prompts using diffusion models, served through the OpenAI-compatible images endpoint. Install an image model once and you can generate from the API, the SDKs, or the Playground.

Generate an image

Send a model and a prompt. Results come back as base64-encoded PNGs in data[].b64_json — decode and write them to disk.

from pendra import Pendra
import base64, pathlib

client = Pendra()
result = client.images.generations.create(
    model="flux.1-schnell",
    prompt="A misty Welsh valley at dawn, painted in oils",
)
pathlib.Path("out.png").write_bytes(base64.b64decode(result.data[0].b64_json))

import Pendra from 'pendra';
import { writeFileSync } from 'node:fs';

const client = new Pendra();
const result = await client.images.generations.create({
  model: 'flux.1-schnell',
  prompt: 'A misty Welsh valley at dawn, painted in oils',
});
writeFileSync('out.png', Buffer.from(result.data[0].b64_json, 'base64'));

Response

Available models

Several text-to-image models are one install away — for example:

• sdxl-turbo — fast 1–4 step generation.
• sdxl-base-1.0 — Stable Diffusion XL base.
• stable-diffusion-1.5 — the classic, small (~2 GB).
• flux.1-schnell — FLUX.1 [schnell], high quality (~10 GB).
• stable-diffusion-3.5-large-turbo — SD 3.5 Large Turbo.
• z-image-turbo — Z-Image Turbo, fast few-step generation.
• flux.2-klein-4b — FLUX.2 klein [4B], fast and compact.
• flux.2-klein-9b — FLUX.2 klein [9B], higher quality.
• qwen-image-2512 — Qwen-Image 2512, strong at rendering text in images.

Browse what's available at /models?type=image.

Options

By default Pendra generates at each model's native resolution — the size it was trained for, which gives the best quality, so you usually don't need to set size at all. That's 512x512 for stable-diffusion-1.5 and sdxl-turbo, and 1024x1024 for sdxl-base-1.0, flux.1-schnell, and stable-diffusion-3.5-large-turbo. You can still request a specific size (WxH) when you need a particular shape — but note that generating far from a model's native resolution can distort the result (for example, duplicated subjects).

Use num_inference_steps to trade speed for quality: more steps generally means a sharper, more coherent image but a slower generation. Like size, it defaults per model — around 30 for the standard checkpoints (stable-diffusion-1.5, sdxl-base-1.0) and just 4 for the distilled "turbo" / "schnell" models (sdxl-turbo, flux.1-schnell, stable-diffusion-3.5-large-turbo), which are built to converge in a handful of steps — so you usually don't need to set it. The newer models ship their own tuned defaults too — around 8 for z-image-turbo and the flux.2-klein models, and 20 for qwen-image-2512 — so the same "leave it unset" advice applies.

Also tune n (up to 4 images), negative_prompt, and seed for reproducibility. Generation is slower than chat — expect a few to thirty seconds depending on model, size, and steps — so render a spinner in interactive UIs.