Trending

qwen-image-edit-2511-trainer

LoRA trainer for Qwen Image Edit 2511

qwen-image-layered-trainer

Train LoRAs for the Qwen-Image-Layered model, customize how images are split into layers.

SCAIL is a character animation model that uses 3D consistent pose representations to animate reference images with coherent motion, supporting complex movements.

Create your imagined 3D models with just text. Production-ready, export-ready professional assets with realistic lighting and materials in minutes.

wan-vision-enhancer

Wan Vision Enhancer for magnify/enhance video with high fidelity and creativity.

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

decart/lucy-edit/fast

Lucy Edit Fast is a rapid, localized video editing model that lets you modify specific elements like objects, or backgrounds in just 10 seconds.

LoRA endpoint for the Chrono Edit model.

You can make edits simply by drawing a quick sketch on the input image.

Upscales and cleans up the image.

bytedance/lynx

Generate subject consistent videos using Lynx from ByteDance!

Edit videos using instruction-based prompting using Editto model!

Leverage Sana's ultra-fast processing speed to generate high-quality assets that transform your text prompts into production-ready videos

Upscale your videos at real-time speeds with Sima Labs!

NVIDIA's Logically Consistent and Physics-Aware Image Editing Model

qwen-image-edit-plus-trainer

LoRA trainer for Qwen Image Edit Plus

qwen-image-edit-trainer

LoRA trainer for Qwen Image Edit

Image-to-3D endpoint for OmniPart, a part-aware 3D generator with semantic decoupling and structural cohesion.

A model for unified semantic control in video generation. It animates a static reference image using the motion and semantics from a reference video as a prompt.

Use the faster speed of piflow to generate images with same quality to that of slower models.

qwen-3-guard

Use Qwen 3 Guard [8B] to detect and classify text as safe or harmful, delivering precise and reliable safety categorization.

wan-alpha

Generate videos with transparent backgrounds

DreamOmni2 is a unified multimodal model for text and image guided image editing.

sora-2/video-to-video/remix

Video-to-video remix endpoint for Sora 2, OpenAI’s advanced model that transforms existing videos based on new text or image prompts allowing rich edits, style changes, and creative reinterpretations while preserving motion and structure