Available models
Below is a complete list of all AI models available in ImageGPT. Each model has different capabilities, quality levels, and credit costs.
Text to image
Nano Banana
Default model for generating images.
Nano Banana Pro
Nano Banana Pro (a.k.a Nano Banana 2) is state-of-the-art image generation and editing model
Bytedance Seedream 4.5
GPT Image 1.5
Flux 2 Pro
Hunyuan Image V3
Wan 2.6
Image to image
Nano Banana Edit
More strict moderation (can not remove watermarks etc)
Nano Banana Pro Edit
Nano Banana Pro (a.k.a Nano Banana 2) is state-of-the-art image generation and editing model
Bytedance Seedream 4.5 Edit
GPT Image 1.5 Edit
Wan 2.6 Edit
Remove background
BiRefNet v2
background removal
Upscale image
Recraft Upscale Crisp
High quality upscaling
Vectorize image
Recraft Vectorize
Convert images to SVG format
Text to video
Sora 2
Best video generation model available can produce video with sound in 720p.
Sora 2 Pro
Can produce up to 1080p videos with sound and music. Very good quality.
Google Veo 3.1 Fast
Image to video
Google Veo 3.1 Fast
Kling Video v2.5 Turbo Pro
Seedance v1 Pro
Seedance v1.5 Pro
Sora 2
Can produce video with sound and music.
Sora 2 Pro
Can produce 1080p videos with sound and music.
Wan 2.5 Preview
Can produce video with sound.
Video to video
Wan v2.2 14B Animate Replace
Model that can replace characters into reference videos, replacing the original character while preserving everything else in the video