Trending

Use the capabilities of hunyuan part to generate point clouds from your 3D files.

sora-2/image-to-video/pro

Image-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

sora-2/text-to-video/pro

Text-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

sora-2/text-to-video

Text-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

sora-2/image-to-video

Image-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

LucidFlux for upscaling images with very high fidelity

Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

decart/lucy-edit/dev

Edit outfits, objects, faces, or restyle your video - all with maximum detail retention.

Use the 6D pose estimation capabilities of PSHuman to generate 3D files from single image.

bytedance/seedance/v1/lite/reference-to-video

Seedance lite reference-to-video allows the use of 1 to 4 images as reference to create a high-quality video.

wan-ati

WAN-ATI is a controllable video generation model that uses trajectory instructions to guide object, local, and camera motion, enabling precise and flexible image-to-video creation.

wan-fun-control

Generate pose or depth controlled video using Alibaba-PAI's Wan 2.2 Fun

Infinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

bria/reimagine/3.2

Reimagine uses a structure reference for generating new images while preserving the structure of an input image, guided by text prompts. Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data

qwen-image-edit

Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.

Stable Avatar generates audio-driven video avatars up to five minutes long

qwen-image-trainer

Qwen Image LoRA training

bytedance/video-stylize

Transform your images into stylized videos using this workflow.

bytedance/dreamina/v3.1/text-to-image

Dreamina showcases superior picture effects, with significant improvements in picture aesthetics, precise and diverse styles, and rich details.

flux-krea-trainer

Train styles, people and other subjects at blazing speeds using the FLUX.1 Krea [dev] base model.

veo3/image-to-video

Veo 3 is the latest state-of-the art video generation model from Google DeepMind

Edit images with natural language

veo3/fast/image-to-video

Now with a 50% price drop. Generate videos from your image prompts using Veo 3 fast.