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 assetsBenchmarksEarn crypto
  1. Models
  2. Image

Custom CivitAI

Try Model

Browse CivitAI models confirmed available in NanoGPT, or search by name, URL, model ID, or exact AIR. Exact checkpoint and LoRA routes are verified before generation.

Added Feb 1, 2026

Details

Approx. Price
$0.005 per image
Model type
both

Settings

Generation controls available for this model.

Images Per Run

Up to 4

Output images

Input Images

Up to 1

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square
Portrait
Landscape
up to 1,920px

CFG Scale

Default

7.5

Controls prompt adherence.

Number of Images

Default

1

Resolution

Default

1024x1024

Options (6)

1024x1024 (Default), 1024x768, 768x1024, 512x512 +2 more

Scheduler

Default

N/A

Sampler/scheduler used by the model (optional).

Steps

Default

20

Number of denoising steps.

Strength

Default

0.8

Image-to-image strength (only used with a seed image).

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related image models

Compare Custom CivitAI with similar models from the same provider or model family.

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, 2K or 3K 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. The API also generates animated GIFs with 2–64 frames. Prices are estimated before generation and settled from actual token usage.

GPT Image 2.6 Sunburst

gpt-image-2.6-sunburst

GPT Image 2.6 Sunburst generates images from text and edits images with up to 16 references. Designed for detailed compositions. 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. The API also generates animated GIFs with 2–64 frames. Prices are estimated before generation and settled from actual token usage.

P-H3 Image

wavespeed-ai/p-h3-image/text-to-image

P-H3 Image by Pruna AI generates and edits photorealistic images at 1K, 1.5K, 2K, 3K or 4K. Edit one image with up to eight additional references, choose from fifteen aspect ratios, and apply up to three compatible LoRAs with strengths from 0 to 4. Refer to inputs as <Picture 1>, <Picture 2> and so on. Outputs are JPEG, PNG or WebP.

FLUX.1 Pro Erase

flux-pro/v1/erase

FLUX.1 Pro Erase by Black Forest Labs removes masked objects and text, filling the area with context-aware detail. Upload one image and a matching black-and-white mask: white removes, black preserves. Adjust mask expansion from 0 to 100 pixels and export JPEG or PNG. Accepts source images up to 4MP; larger outputs are resized to about 2MP. No text prompt is needed.