Explore

Fine-tune FLUX fast
Customize FLUX.1 [dev] with the fast FLUX trainer on Replicate
Train the model to recognize and generate new concepts using a small set of example images, for specific styles, characters, or objects. It's fast (under 2 minutes), cheap (under $2), and gives you a warm, runnable model plus LoRA weights to download.
Featured models

black-forest-labs / flux-kontext-dev
Open-weight version of FLUX.1 Kontext

bytedance / seedream-3
A text-to-image model with support for native high-resolution (2K) image generation
bytedance / seedance-1-pro
A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution

bytedance / seedance-1-lite
A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution

kwaivgi / kling-v2.1
Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)

google / veo-3
Sound on: Google’s flagship Veo 3 text to video model, with audio

google / imagen-4-ultra
Use this ultra version of Imagen 4 when quality matters more than speed and cost

black-forest-labs / flux-kontext-pro
A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

black-forest-labs / flux-kontext-max
A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
Official models
Official models are always on, maintained, and have predictable pricing.
I want to…
Generate images
Models that generate images from text prompts
Generate videos
Models that create and edit videos
Edit images
Tools for editing images.
Upscale images
Upscaling models that create high-quality images from low-quality images
Generate speech
Convert text to speech
Transcribe speech
Models that convert speech to text
Use LLMs
Models that can understand and generate text
Caption videos
Models that generate text from videos
Make 3D stuff
Models that generate 3D objects, scenes, radiance fields, textures and multi-views.
Restore images
Models that improve or restore images by deblurring, colorization, and removing noise
Generate music
Models to generate and modify music
Caption images
Models that generate text from images
Make videos with Wan2.1
Generate videos with Wan2.1, the fastest and highest quality open-source video generation model.
Use handy tools
Toolbelt-type models for videos and images.
Control image generation
Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.
Extract text from images
Optical character recognition (OCR) and text extraction
Chat with images
Ask language models about images
Sing with voices
Voice-to-voice cloning and musical prosody
Get embeddings
Models that generate embeddings from inputs
Use a face to make images
Make realistic images of people instantly
Remove backgrounds
Models that remove backgrounds from images and videos
Try for free
Get started with these models without adding a credit card. Whether you're making videos, generating images, or upscaling photos, these are great starting points.
Use the FLUX family of models
The FLUX family of text-to-image models from Black Forest Labs
Use official models
Official models are always on, maintained, and have predictable pricing.
Enhance videos
Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.
Detect objects
Models that detect or segment objects in images and videos.
Use FLUX fine-tunes
Browse the diverse range of fine-tunes the community has custom-trained on Replicate
Popular models
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
This is the fastest Flux Dev endpoint in the world, contact us for more at pruna.ai
Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Return CLIP features for the clip-vit-large-patch14 model
whisper-large-v3, incredibly fast, powered by Hugging Face Transformers! 🤗
Latest models
T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor
T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor
A 7 billion parameter language model from Meta, fine tuned for chat completions
SDXL v1.0 - A text-to-image generative AI model that creates beautiful images
Tuning-Free Longer Video Diffusion via Noise Rescheduling
Zephyr-7B-beta, an LLM trained to act as a helpful assistant.
Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)
FILM: Frame Interpolation for Large Motion, In ECCV 2022.
Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)
Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)
A 40 billion parameter language model trained to follow human instructions.
An English, monolingual embedding model supporting 8192 sequence length (137M version)
Source: HuggingFaceH4/zephyr-7b-beta ✦ Quant: TheBloke/zephyr-7B-beta-AWQ ✦ Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series
This is a cog implementation of "openbuddy-llemma-34b" 4-bit quantization model.
Mask prompting based on Grounding DINO & Segment Anything | Integral cog of doiwear.it
A 6B parameter open bilingual chat LLM (optimized for 8k+ context) | 开源双语对话语言模型
Openbuddy finetuned mistral-7b in GPTQ quantization in 4bits by TheBloke
A 8k sequence length text embedding set trained by Jina AI
MistralLiteA is a fine-tuned Mistral-7B-v0.1 language model, with enhanced capabilities of processing long context (up to 32K tokens)
controlnet 1.1 lineart x realistic-vision-v2.0 (updated to v5)
BakLLaVA-1 is a Mistral 7B base augmented with the LLaVA 1.5 architecture
Source: teknium/Mistral-Trismegistus-7B ✦ Quant: TheBloke/Mistral-Trismegistus-7B-AWQ ✦ Mistral Trismegistus is a model made for people interested in the esoteric, occult, and spiritual
Source: bavest/fin-llama-33b ✦ Quant: TheBloke/fin-llama-33B-AWQ ✦ Efficient Finetuning of Quantized LLMs for Finance
😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL
Source: migtissera/Synthia-13B-v1.2 ✦ Quant: TheBloke/Synthia-13B-v1.2-AWQ ✦ SynthIA (Synthetic Intelligent Agent) is a LLama-2-13B model trained on Orca style datasets
Source: ajibawa-2023/carl-llama-2-13b ✦ Quant: TheBloke/Carl-Llama-2-13B-AWQ ✦ Carl: A Therapist AI