Models (3)·续1
Compare
<h3>flux-2-pro-preview</h3>Black Forest LabsText-to-Image FLUX.2 [pro] Preview is Black Forest Labs' recommended default for production image generation and editing — tracks the latest [pro] weights with strong multi-reference support.
Compare
<h3>flux-3-image-klein</h3>Black Forest LabsText-to-Image FLUX 3 Image Klein is Black Forest Labs' 5.6B-parameter image model for text-to-image, image editing, and multi-reference generation with up to 10 reference images. It supports native 4K output and bounding-box layout control.
Compare
<h3>flux-3-video</h3>Black Forest LabsText-to-Video FLUX 3 Video is Black Forest Labs' video generation model. It generates video from a text prompt (t2v), animates one or more reference images (i2v), or continues an existing clip (v2v), with synchronized audio, up to fhd resolution, and 5-20 second durations.
Compare
<h3>flux-video-upscale</h3>Black Forest Labsvideo-to-video FLUX Video Upscale increases video resolution with a precise mode for source-faithful results and a creative mode for stronger detail enhancement. It accepts clips up to 20 seconds and preserves audio.
Compare
b<h3>ad-delayer</h3>briaImage-to-Document Ad Delayer turns a finished, flat ad image into an editable JSON layer document: a background plate, product and logo cutouts, live text with typography, and vector shapes, with each image layer hosted as its own file. It is designed for flat ads; results for ordinary photographs are not guaranteed. Bria trains it exclusively on licensed data.
Compare
b<h3>fibo-edit-1.5</h3>briaImage-to-Image FIBO Edit changes one to four input images from a natural-language or structured JSON (VGL) instruction. Add a black-and-white mask to edit only part of a single image, or refer to several images as "image 1", "image 2", and so on to combine them or transfer a style.
Compare
b<h3>fibo-generate-1.5</h3>briaText-to-Image FIBO Generate creates images from a text prompt, a reference image, or both. Each result includes the seed and the structured JSON (VGL) prompt used to render it; send them back to recreate the image exactly or to refine it with a new prompt. Outputs are 1MP or 4MP in nine aspect ratios.
Compare
b<h3>remove-background</h3>briaImage-to-Image Bria's RMBG 2.0 model removes the background from an image and returns a PNG cutout with a transparent background. Partial transparency from the input's alpha channel is kept by default.
Compare
b<h3>v-rmbg-3.0</h3>briavideo-to-video Bria's video background removal replaces the background of a clip up to 60 seconds long with a solid color or with transparency. Transparent output needs the mov_proresks (ProRes) preset. Frame rate and audio are preserved, and the output resolution matches the input unless auto_zoom crops to the subject.
Compare
<h3>seedance-2.0</h3>ByteDanceText-to-Video ByteDance's next-generation video model with a unified multimodal architecture. Generates high-quality video with synchronized audio from text, images, video clips, and audio inputs. Supports multimodal references (up to 9 images, 3 videos, 3 audio files), native audio generation, video editing, video extension, intelligent duration, and adaptive aspect ratio.
Compare
<h3>seedance-2.0-fast</h3>ByteDanceText-to-Video Faster variant of ByteDance's Seedance 2.0 video model. Trades some quality for speed while sharing the same multimodal architecture. Supports text-to-video, image-to-video, native audio generation, multimodal references (images, videos, audio), video editing, and video extension.
Compare
<h3>seedance-2.0-mini</h3>ByteDanceText-to-Video ByteDance's compact, cost-efficient video generation model from the Seedance 2.0 family. Supports text-to-video, image-to-video, reference video, and reference audio for background music. Ideal for high-volume workloads where speed and cost matter.
Compare
<h3>seedance-2.5</h3>ByteDanceText-to-Video ByteDance's next-generation video model with a unified multimodal reference-to-video architecture. Generates video from text, up to 30 reference images, 10 reference videos, and 10 reference audio clips — including audio-only input with no image or video required. Supports first/last-frame image-to-video, video editing, video extension, intelligent duration (including automatic selection), and adaptive aspect ratio.
Compare
<h3>seedream-4.0</h3>ByteDanceText-to-Image Seedream 4.0 is ByteDance's image creation model that combines text-to-image generation and image editing into a single architecture, offering fast, high-resolution output up to 4K.
Compare
<h3>seedream-4.5</h3>ByteDanceText-to-Image Seedream 4.5 builds on 4.0 with multi-reference image support, batch generation, and sequential image generation.
Compare
<h3>seedream-5-lite</h3>ByteDanceText-to-Image Seedream 5 Lite is a lighter, faster version of the Seedream 5 family with multi-reference and batch generation support.
Compare
<h3>seedream-5-pro</h3>ByteDanceText-to-Image Seedream 5 Pro is ByteDance's high-quality image generation and editing model with text prompts, up to 10 reference images, and 1K, 2K, or explicit pixel-size output controls.
Compare
d<h3>deepseek-v4-pro</h3>deepseekText Generation DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek, served via Fireworks infrastructure for production-grade inference.
Compare
<h3>eleven-flash-v2-5</h3>ElevenLabsText-to-Speech ElevenLabs' low-latency Flash v2.5 text-to-speech model for fast multilingual speech generation.
Compare
<h3>eleven-multilingual-v2</h3>ElevenLabsText-to-Speech ElevenLabs' multilingual text-to-speech model for generating natural speech across many languages with ElevenLabs voices.
Compare
<h3>eleven-turbo-v2-5</h3>ElevenLabsText-to-Speech ElevenLabs' Turbo v2.5 text-to-speech model balancing high-quality voice generation with low latency across 32 languages.
Compare
<h3>eleven-v3</h3>ElevenLabsText-to-Speech ElevenLabs' latest text-to-speech model for highly expressive, natural speech generation with advanced voice control.
Compare
<h3>music-v2</h3>ElevenLabsMusic Generation ElevenLabs Music v2 composes songs and instrumental tracks from a prompt or detailed composition plan.
Compare
<h3>ember-1</h3>FireworksText Generation Fireworks' Ember-1 is a specialized long-context multimodal reasoning model built on Kimi K3. It produces shorter reasoning traces using approximately 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations.
Compare
<h3>gemini-2.5-flash</h3>GoogleText Generation Google's fast multimodal Gemini 2.5 model with strong reasoning and a 1M token context window.
Compare
<h3>gemini-2.5-flash-lite</h3>GoogleText Generation Google's lightest and most cost-efficient Gemini 2.5 model for high-throughput tasks.
Compare
<h3>gemini-2.5-pro</h3>GoogleText Generation Google's most capable Gemini 2.5 model with strong reasoning, thinking support, and a 1M token context window.
Compare
<h3>gemini-3-flash</h3>GoogleText Generation Gemini 3 Flash is Google's fast multimodal model with frontier intelligence, superior search, and grounding capabilities.
Compare
<h3>gemini-3.1-flash-lite</h3>GoogleText Generation Google's lightest and most cost-efficient Gemini model for high-throughput tasks.
Compare
<h3>gemini-3.1-flash-tts</h3>GoogleText-to-Speech
Compare
<h3>gemini-3.1-pro</h3>GoogleText Generation Google's most intelligent Gemini model with improved reasoning, a medium thinking level, and a 1M token context window.
Compare
<h3>gemini-3.5-flash</h3>GoogleText Generation Gemini 3.5 Flash is Google's fast multimodal model with frontier intelligence, superior search, and grounding capabilities.
Compare
<h3>gemini-3.5-flash-lite</h3>GoogleText Generation Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing.
Compare
<h3>gemini-3.6-flash</h3>GoogleText Generation Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost, excelling at code generation, agentic execution, and spatial reasoning.
Compare
<h3>gemini-3.7-flash</h3>GoogleText Generation Gemini 3.7 Flash is a highly capable, natively multimodal reasoning model optimized for agentic workflows and real-world tasks.
Compare
<h3>gemini-3.8-flash</h3>GoogleText Generation Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
Compare
<h3>gemini-3.8-flash-lite-tts</h3>GoogleText-to-Speech Gemini 3.8 Flash-Lite TTS is a fast, cost-efficient text-to-speech model optimized for high-throughput production workloads.
Compare
<h3>gemini-3.8-flash-tts</h3>GoogleText-to-Speech Gemini 3.8 Flash TTS is Google's flagship text-to-speech model for expressive, natural speech generation.
Compare
<h3>gemini-4-argon</h3>GoogleText Generation Google's frontier model for deep work on complex, real-world tasks across coding, finance, legal, cybersecurity and science. The first model in the Gemini 4 family.
Compare
<h3>gemini-omni-1.1-flash</h3>GoogleText-to-Video High-performance multimodal video generation and editing model with conversational controls and generated audio.
我的书签
添加书签
移除书签
