Omnipix
Generative models in Omnipix
Explore supported image, video, audio, avatar, and enhancement models. Compare capabilities, learn the controls, and open a model directly in Omnipix.
41 results
Alibaba
View detailsBlack Forest Labs
View detailsEnhance
FLUX Tools
Purpose-built FLUX workflows for object removal, canvas expansion, garment try-on, and deblurring.
Image
FLUX.2
FLUX.2 image generation and reference-guided editing, with variants tuned for speed, control, or final-asset quality.
Video
FLUX.3 Video
FLUX.3 generates video from text, timed image keyframes, or a source clip, with reusable drafts for full-quality enhancement.
ByteDance
View detailsVideo
Seedance 1.5
Seedance 1.5 Pro jointly generates picture and sound from text or an opening image, with optional last-frame guidance.
Video
Seedance 2
Seedance 2.5 is the flagship text and multimodal-reference model, while Seedance 2.0 offers standard, Fast, Mini, and LR alternatives.
Recommended
Standard Seedance may refuse harmless prompts and synthetic people. Start with LR for substantially fewer moderation false positives; choose Full LR, Fast LR, or Mini LR for the quality and speed you need.
Image
Seedream 4.5
Seedream 4.5 image generation and reference-guided editing with 2K or 4K output and strong multi-image consistency.
Image
Seedream 5
Seedream 5 image generation and reference-guided editing across Pro and Lite configurations.
ElevenLabs
View detailsFreepik
View details
Image
Gemini Image
Google's Nano Banana image models for prompt-driven creation, text rendering, and version-dependent reference editing.
Video
Gemini Omni Video
Gemini Omni Flash Preview creates and edits short 720p videos with native audio from text, images, and video context.
Video
Veo 3.1
Google Veo 3.1 creates video with native audio from text, a starting image, first and last frames, or reference images.
HeyGen
View detailsAvatar
HeyGen Avatar Creation
Create a reusable HeyGen Photo Avatar from one authorized still image.
Audio
HeyGen Starfish TTS
Generate spoken audio from text with a saved Starfish-compatible HeyGen voice and adjustable delivery speed.
Video
HeyGen Video
HeyGen creates complete videos and talking avatars, translates footage, and synchronizes supplied audio with an existing speaker.
Kling AI
View detailsVideo
Kling 2.5 Turbo
Kling 2.5 Turbo provides text-to-video and image-to-video variants in Standard and Pro configurations.
Video
Kling Avatar v2
Kling Avatar v2 turns one portrait and a speech recording into a synchronized talking-avatar video.
Video
Kling Motion Control
Kling Motion Control transfers the movement from a reference video to the character or scene shown in a reference image.
Video
Kling O1
Kling O1 combines text, first and last frames, image references, video references, and natural-language video editing in one model.
Video
Kling Omni Video
Kling Video 3.0 Omni unifies text, image, reference, and video-editing workflows with optional native audio and multi-shot prompting.
Luma AI
View detailsMiniMax
View detailsVideo
Hailuo Video
MiniMax Hailuo generates video from text, a first frame, or first and last frames, with Standard and Fast model variants.
Audio
MiniMax Speech
Generate multilingual speech with a preset or compatible cloned MiniMax voice and detailed delivery controls.
Audio
MiniMax Voice Cloning
Create a reusable MiniMax voice ID from an authorized reference recording for compatible speech generation.
OpenAI
View details
Runway
View detailsTopaz Labs
View detailsEnhance
Topaz Color and Lighting
Topaz models for exposure recovery, white-balance correction, and context-aware colorization of monochrome images.
Enhance
Topaz Frame Interpolation
Topaz Frame Interpolation synthesizes intermediate frames to change frame rate or create slow motion with Aion, Apollo, and Chronos.
Enhance
Topaz Image Cleanup
Topaz cleanup workflows for background isolation, archival dust and scratch repair, and object-aware reconstruction.
Enhance
Topaz Image Denoise
Topaz denoising from everyday low-light cleanup to severe noise removal and generative detail recovery.
Enhance
Topaz Image Sharpen
Topaz sharpening models for lens blur, motion blur, portraits, wildlife, natural texture, and severe focus recovery.
Enhance
Topaz Image Upscale
Topaz upscaling models specialized for photos, low-resolution sources, CGI, text, transparency, faces, and generative reconstruction.
Enhance
Topaz Video Denoise
Topaz Nyx models reduce sensor noise and grain, from fast previews and strong cleanup to fidelity-preserving denoise-only processing.
Enhance
Topaz Video Upscale
Topaz Video Upscale groups restoration, deinterlacing, face recovery, general enhancement, and diffusion-based models for different source defects.
Enhance
Topaz Video Utilities
Topaz Video Utilities covers three separate operations: SDR-to-HDR conversion, motion deblur, and black-and-white video colorization.
