Replicate Models
1,173 entities
jemov/fiojeklnb
modelvufinder/map-anything-pi3
modelA feed-forward neural network that offers a novel approach to visual geometry reconstruction.
quiverai/arrow-1.1-vectorize
modelConvert raster images (PNG, JPEG, WebP) into clean SVGs with Quiver's Arrow 1.1 vectorization model. Great for turning logos and icons into editable vectors.
anthropic/claude-fable-5.2
modelAnthropic's model for the most demanding reasoning and long-horizon agentic work, at 20% less per token than Fable 5
kwaivgi/kling-v4-flash
modelKling 4.0 Flash: a faster, cheaper Kling 4.0 that makes 3 to 20 second 720p videos with sound from text, a first frame, reference images, or reference videos, and edits existing videos
google/gemini-4-carbon
modelGoogle's strongest reasoning model, built for complex coding, science, and long multi-step tasks
google/lyria-3.5
modelGenerate full-length songs with vocals and lyrics from text prompts or images with Lyria 3.5, Google's most capable music generation model
minimax/h3
modelGenerate videos with MiniMax H3, a multimodal video model from MiniMax that supports text-to-video, first- and last-frame image-to-video, and reference-based video generation.
google/gemini-omni-1.2-flash
modelGoogle's video generation and editing model with native audio. Makes 3 to 15 second clips from text, images, reference images, or an existing video.
openai/gpt-image-2.6-flare
modelOpenAI's fast image model for generating and editing images from text and image inputs. Adds a complexity setting that controls how much the model plans before it renders.
openai/gpt-image-2.6-sunburst
modelOpenAI's image model for detailed compositions and precise edits. Generate and edit images from text and image inputs, with a complexity setting that controls how much the model plans before it renders.
prunaai/p-video-2-pro-replace
modelPruna's person-swap model. Put the person from a picture into a source video, keep the camera, motion, and soundtrack, from 1 to 120 seconds and 480p to 4K.
prunaai/llada2.1-mini
modelThe fastest diffusion language model with up to ~1000+ tps
recraft-ai/recraft-v4-styles-pro
modelRecraft V4 Styles Pro generates 2K raster images that match a reusable style or attached reference images. Built for print-ready, style-consistent assets.
minimax/h3-highspeed
modelGenerate videos with MiniMax H3 Highspeed, a faster version of MiniMax H3 that balances quality and speed. Supports text-to-video, first- and last-frame image-to-video, and reference-based video generation at 768P.
minimax/h3-lite
modelGenerate videos with MiniMax H3 Lite, the lower-cost version of MiniMax H3. Supports text-to-video, first- and last-frame image-to-video, and reference-based video generation at 480P or 768P.
prunaai/p-video-upscale
modelPruna's video upscaler. Turn a low-resolution clip into a sharper 720p, 1080p, 2K, or 4K MP4 that keeps the original aspect ratio and audio, with optional frame interpolation up to 60 fps.
google/gemini-3.8-flash-lite-tts
modelGoogle's fast, low-cost text-to-speech model with line-by-line delivery direction, vocal bursts, and two-speaker dialogue in 100+ languages
google/gemini-3.8-flash-tts
modelGoogle's most expressive text-to-speech model, with line-by-line delivery direction, vocal bursts, two-speaker dialogue, and 130+ languages
kwaivgi/kling-v4.0
modelKling 4.0: generate 3 to 30 second videos at up to 1080p from text, keyframes, reference images, or reference videos, and edit existing videos
pixverse/pixverse-v6-max
modelPixVerse's highest-quality video model. Generate up to 15 seconds of 1080p video with synchronized audio, from text or an image.
prunaai/p-video-2-pro-avatar
modelPruna's talking-avatar model. Turn a portrait and an audio file or script into a talking video with synced lips and expressions, from 1 second to 3 minutes long.
anthropic/claude-opus-5.5
modelAnthropic's Opus model for long-running agentic coding and knowledge work, at a lower price than Opus 5
replicate/flux-3-klein-image-lora
modelGenerate images from Flux 3 Klein Image using your own LoRA
quiverai/arrow-1.1-max-vectorize
modelConvert complex raster images into high-fidelity SVGs with Quiver's Arrow 1.1 Max vectorization model. Tuned for detailed images where fine structure and alignment matter.
Page 1 of 47