Explore
Featured models
prunaai / hidream-l1-fast
This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
ibm-granite / granite-3.3-8b-instruct
Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
meta / llama-4-maverick-instruct
A 17 billion parameter model with 128 experts
meta / llama-4-scout-instruct
A 17 billion parameter model with 16 experts
nvidia / sana-sprint-1.6b
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
black-forest-labs / flux-dev-lora
A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
wavespeedai / wan-2.1-i2v-480p
Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
anthropic / claude-3.7-sonnet
The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)
kwaivgi / kling-v1.6-standard
Generate 5s and 10s videos in 720p resolution
I want to…
Make videos with Wan2.1
Generate videos with Wan2.1, the fastest and highest quality open-source video generation model.
Generate images
Models that generate images from text prompts
Generate videos
Models that create and edit videos
Caption images
Models that generate text from images
Transcribe speech
Models that convert speech to text
Use a face to make images
Make realistic images of people instantly
Generate text
Models that can understand and generate text
Upscale images
Upscaling models that create high-quality images from low-quality images
Use official models
Official models are always on, maintained, and have predictable pricing.
Restore images
Models that improve or restore images by deblurring, colorization, and removing noise
Enhance videos
Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.
Generate speech
Convert text to speech
Caption videos
Model s that generate text from videos
Remove backgrounds
Models that remove backgrounds from images and videos
Use handy tools
Toolbelt-type models for videos and images.
Detect objects
Models that detect or segment objects in images and videos.
Generate music
Models to generate and modify music
Sing with voices
Voice-to-voice cloning and musical prosody
Make 3D stuff
Models that generate 3D objects, scenes, radiance fields, textures and multi-views.
Chat with images
Ask language models about images
Extract text from images
Optical character recognition (OCR) and text extraction
Get embeddings
Models that generate embeddings from inputs
Use the FLUX family of models
The FLUX family of text-to-image models from Black Forest Labs
Use FLUX fine-tunes
Browse the diverse range of fine-tunes the community has custom-trained on Replicate
Control image generation
Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.
Edit images
Tools for manipulating images.
Popular models
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
Generate CLIP (clip-vit-large-patch14) text & image embeddings
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Latest models
This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.
Classifies text with fine tuned BERT. The model handles batched input texts in a single API call to improve performance and reduce costs.
This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
This is an optimised version of the hidream-full model using the pruna ai optimisation toolkit!
This is an optimised version of the hidream-l1-dev model using the pruna ai optimisation toolkit!
Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
The model transforms real-life image to Ghibli Style Art Images.
DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths.
Spanish and English Text to Speech model from Canopy Labs (3b-es_it-ft-research_release)
GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.
This model is an optimised version of stable-diffusion by stability AI that is 3x faster and 3x cheaper.
An optimized version of sdxl-lightning from Bytedance that is more than 2x faster and 2x cheaper
This is an optimised version of the flux schnell model from black forest labs with the pruna tool. We achieve a ~3x speedup over the original model with minimal quality loss.
Mediapipe Blendshape Labeler - Predicts the blend shapes of an image.
Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA
Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner.
Generates realistic talking face animations from a portrait image and audio using the CVPR 2025 Sonic model
Transform your portrait photos into any style or setting while preserving your facial identity
Wan 2.1 1.3b Video to Video. Wan is a powerful visual generation model developed by Tongyi Lab of Alibaba Group
Easily create video datasets with auto-captioning for Hunyuan-Video LoRA finetuning
Cost-optimized MMAudio V2 (T4 GPU): Add sound to video using this version running on T4 hardware for lower cost. Synthesizes high-quality audio from video content.