Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation.

veed/avatars/text-to-video

Generate high-quality videos with UGC-like avatars from text

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

veed/video-background-removal/green-screen

Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.

bernini-r/edit-video

Edit any video with a natural-language instruction using Bernini-R, changing objects, weather, background, or camera angle while keeping the rest of the scene intact.

Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.

bernini-r/reference-to-video

Turn up to five reference images into one continuous, consistent video with Bernini-R, with smooth, stable camera motion and no scene cuts.

Turn your casual photos into stunning professional studio portraits with perfect lighting and high-end photography style.

qwen-image-edit-plus-lora-gallery/add-background

Add a realistic scene behind the object with white background

Any pose, any style, any identity

Generate realistic audio from a video with an optional text prompt

pixverse/sound-effects

Add immersive sound effects and background music to your videos using PixVerse sound effects generation

Generate 3D models from text descriptions using Tripo P1.

Perfect your photos with professional color grading, balanced tones, and vibrant yet natural colors

Run Any Stable Diffusion model with customizable LoRA weights.

Stable Audio 3 Medium Base is the foundational 1.4 billion parameter text-to-audio checkpoint generating stereo music up to 6 minutes, intended as the unmodified base for custom fine-tuning workflows.

wan-vace-14b/reframe

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Edit videos using instruction-based prompting using Editto model!

bria/video/erase/mask

High-fidelity mask-based video object removal with strong temporal consistency. Erase unwanted objects, people, or elements while preserving aesthetic quality. Trained on licensed data for risk-free commercial use.

wan-vace-apps/video-edit

Edit videos using plain language and Wan VACE

Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation.

Ovis-Image is a 7B text-to-image model specifically optimized for quick, high quality text rendering.

kling-video/v1.6/standard/effects

Generate video clips from your prompts using Kling 1.6 (std)

Animate your ideas!

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks