VideoVerifiedPublic
skytells/lumo
by Skytells
Lumo is an image-to-video video model specifically made for motion, animations and general use cases
image-to-video
$1.12/predictionTry it
Explore AI Models
47 models from Skytells and the community
Showing 21–30 of 47 models
VideoVerifiedPublic
skytells/mera
by Skytells
Our latest video generation model is more physically accurate, super realistic, and more controllable than prior systems.
image-to-videotext-to-video+2
$3.42/predictionTry it
VideoVerifiedPublic
skytells/mera-1.1-fast
by Skytells
Mera 1.1 Fast is our latest flagship video generation model, combining Mera’s precision with advances from major video generation models to deliver fast inference, rapid draft previews, robust lipsync, built-in audio generation, and highly controllable text-to-video, image-to-video, and audio-to-video creation with up to 1080p at 48 FPS, multi-aspect ratio support, and prompt upsampling for more realistic, physically accurate results.
image-to-videotext-to-video+2
$0.03/secondTry it
VideoVerifiedPublic
skytells/mera-avatar
by Skytells
Mera Avatar is our latest flagship video generation model, engineered to deliver exceptional speed, realism, and creative control. Built on Mera's advanced architecture and enhanced with innovations inspired by the latest breakthroughs in video generation, Mera Avatar supports text-to-video, image-to-video, and audio-to-video workflows with remarkably fast inference and rapid draft previews. It features robust lip synchronization, native audio generation, prompt upsampling for richer scene understanding, and highly controllable generation, producing physically accurate, cinematic results in up to 1080p resolution at 48 FPS, with full multi-aspect ratio support for every creative workflow.
image-to-videotext-to-video+4
$0.035/secondTry it
VideoVerifiedPublic
skytells/mera-recast
by Skytells
Mera Recast is a high-speed AI model for character replacement in video. Built on an optimized Wan-based architecture and enhanced with technologies from our flagship Mera model, it delivers fast inference, strong identity preservation, temporal consistency, and high-quality results for production-ready video editing.
video-to-videoreplace+5
$0.04/secondTry it
ImageVerifiedPublic
google/nano-banana
by Google
Google's latest image editing model in Gemini 2.5
image-to-imagetext-to-image+2
$0.06/imageTry it
ImageVerifiedPublic
nvidia/nvidia-sana
by Nvidia
A fast image model with wide artistic range and resolutions up to 4096x4096
text-to-image
$0.05/imageTry it
VideoVerifiedPublic
openai/sora-2
by OpenAI
OpenAI's Most advanced synced-audio video generation
image-to-videotext-to-video+1
$0.002/videoTry it
VideoVerifiedPublic
openai/sora-2-pro
by OpenAI
OpenAI's Most advanced synced-audio video generation
image-to-videotext-to-video+1
$0.002/videoTry it
ImageVerifiedPublic
skytells/truefusion
by Skytells
TrueFusion Standard
text-to-image
$0.03/imageTry it
Page 3 of 5
Start building today
One API. Hundreds of models.
Access cutting-edge AI models through a single, unified API. Start with 1,000 free calls — no credit card required.