Explore
batouresearch/high-resolution-controlnet-tile
UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.
stability-ai/stable-diffusion-3
A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency
zsxkib/ic-light
✍️✨Prompts to auto-magically relights your images
snowflake/snowflake-arctic-instruct
An efficient, intelligent, and truly open-source language model
meta/meta-llama-3-70b-instruct
A 70 billion parameter language model from Meta, fine tuned for chat completions
suno-ai/bark
🔊 Text-Prompted Generative Audio Model
I want to…
Generate images
Models that generate images from text prompts
Use a language model
Models that can understand and generate text
Caption images
Models that generate text from images
Edit images
Tools for manipulating images.
Restore images
Models that improve or restore images by deblurring, colorization, and removing noise
Upscale images
Upscaling models that create high-quality images from low-quality images
Get embeddings
Models that generate embeddings from inputs
Train a language model
Language models that you can fine-tune using Replicate's training API.
Chat with images
Ask language models about images
Transcribe speech
Models that convert speech to text
Extract text from images
Optical character recognition (OCR) and text extraction
Use a face to make images
Make realistic images of people instantly
Use handy tools
Toolbelt-type models for videos and images.
Generate music
Models to generate and modify music
Generate videos
Models that create and edit videos
Generate speech
Convert text to speech
Make 3D stuff
Models that generate 3D objects, scenes, radiance fields, textures and multi-views.
Get structured data
Language models that support grammar-based decoding as well as jsonschema constraints.
Popular models
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities
A text-to-image generative AI model that creates beautiful images
Return CLIP features for the clip-vit-large-patch14 model
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.
Latest models
A style that creates a paint wash, great for anime.
A style model, ligne claire esque with eastern influence
A very blocky and bold cartoon style with some anime elements. You should use daiton style to trigger the image generation.
A model that makes a soft and quiet world. Can use "daiton" as a trigger but it isn't needed.
Real-Time High Quality Lip Synchronization with Latent Space Inpainting
MiniCPM LLama3-V 2.5, a new SOTA open-source VLM that surpasses GPT-4V-1106 and Phi-128k on a number of benchmarks.
An improved outpainting model that supports LoRA urls. This model uses PatchMatch to improve the mask quality.
A fast high quality SD 1.5 model, Realistic Vision V6.0 B1 Hyper
High quality 6-step lightning model, Jib Mix Realistic XL v10 Lightning
Fast and high quality lightning model, epiCRealismXL-Lightning Hades
Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!
An example using Garden State Llama to ReFT on the Golden Gate bridge.
🎙️Hololive text-to-speech and voice-to-voice (Japanese🇯🇵 + English🇬🇧)
epiCRealism v7-Final Destination. Top Realism Model on Civitai
blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1, The top ranked model on Civitai
AI that transforms sketches into realistic images. Upload your drawing and describe it in the prompt. You can also adjust the ControlNet parameters and scale the image to a higher resolution for better results
A PhotoBooth style transfer workflow that utilizes IPadapter Style, Canny, OpenPose, RemoveBackground, HumanSegmentation, Cloth Segmentation for initial input, and concludes with the application of DeepFake techniques.
AI Photorealistic Image Ultra-Resolution, Restoration and Upscale!
SDXL LoRA finetuned on spectrograms of Beethoven songs
Transfer empty room into fabulous interior design
Interior remodelling, keeps windows, ceilings, and doors. Uses a depth controlnet weighted to ignore existing furniture.
COMPP FS24 - A fine tuned model of MusicGen for continuation of music files in the style of System of a Down.
