Train styles, people and other subjects at blazing speeds.

Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts audio plus a prompt and returns text.

Train a custom LoRA on your own images to teach Krea 2 a new subject, character, or style. Provide a set of training images (and an optional trigger word), and the trainer outputs LoRA weights you can use for inference with the Krea 2 LoRA endpoint.

FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.

Fine-tune FLUX 3 Image Klein with your own images to teach it a subject, a product or a style.

Train LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.

Turn images or video into a detailed 3D scene with depth, camera poses, and a colored point cloud.

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.

Turn any flat ad image into fully editable layers —background, product and logo cutouts, live text with typography, and vector shapes. Commercial-safe, structured JSON output

Qwen Image 2512 LoRA training

Fast LoRA trainer for Z-Image-Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Fine-tune FLUX 3 Image Klein on before/after image pairs to teach it a custom edit, with up to 10 input images per pair.

Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model

A blazing fast FLUX dev LoRA trainer for subjects and styles.

Analyzes an uploaded song and returns its duration and recognized lyrics with timing information when available.

Analyzes a song from an audio URL and returns a written description, identified instruments, genres, and descriptive tags.

Creates a reusable style from your reference images and returns a style ID you can pass to Recraft V4 Styles image and vector generation.

Choose the Nth image from an image URL list for workflows.

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

Train LTX-2.3 22B for custom styles and effects.

Generate profiles using 30-50 images of a subject with Phota.

LoRA trainer for FLUX.1 Kontext [dev]