Explore
Featured models
black-forest-labs / flux-canny-pro
Professional edge-guided image generation. Control structure and composition using Canny edge detection
black-forest-labs / flux-fill-pro
Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.
black-forest-labs / flux-1.1-pro-ultra
FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
black-forest-labs / flux-redux-dev
Open-weight image variation model. Create new versions while preserving key elements of your original.
recraft-ai / recraft-v3
Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis
davisbrown / flux-half-illustration
Flux lora, use "in the style of TOK" to trigger generation, creates half photo half illustrated elements
I want to…
Generate images
Models that generate images from text prompts
Use a language model
Models that can understand and generate text
Upscale images
Upscaling models that create high-quality images from low-quality images
Caption images
Models that generate text from images
The FLUX family of models
The FLUX family of text-to-image models from Black Forest Labs
Restore images
Models that improve or restore images by deblurring, colorization, and removing noise
Get embeddings
Models that generate embeddings from inputs
Extract text from images
Optical character recognition (OCR) and text extraction
Transcribe speech
Models that convert speech to text
Use handy tools
Toolbelt-type models for videos and images.
Chat with images
Ask language models about images
Edit images
Tools for manipulating images.
Use a face to make images
Make realistic images of people instantly
Flux fine-tunes
Browse the diverse range of fine-tunes the community has custom-trained on Replicate
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
A simple OCR Model that can easily extract text from an image.
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification
Real-ESRGAN with optional face correction and adjustable upscale
Latest models
A wrapper model for captioning multiple images using GPT, Claude or Gemini, useful for lora training
Fine-tuned LLaVa model for youtube thumbnail classification
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.
FLUX.1-Dev LoRA trainer via SimpleTuner (Work in Progress)
"MusiConGen: Rhythm and chord control for Transformer-based text-to-music generation"
AuraSR v2: Second-gen GAN-based Super-Resolution for real-world applications
MT3: Multi-Task Multitrack Music Transcription
Segment Anything 2 (SAM2) by Meta - Automatic mask generation
Change the background on an image and relight the scene.
LLaMA 3.1-8B, finetuned on a synthetic OCR dataset for superior OCR correction.
multilingual-e5-large-instruct: A multi-language text embedding model with custom query instructions.
moondream2 is a small vision language model designed to run efficiently on edge devices
Huggingface Diffusers: SDv1.4/1.5/2.0/2.1 finetuner
Inpaint a selected area of an image using controlnet union for SDXL.
Outpaint an image using controlnet union for SDXL.
Bilateral Reference for High-Resolution Dichotomous Image Segmentation (CAAI AIR 2024)
A fully open-sourced, large flow-based text-to-image generation model
LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to subvert the developer’s intended behavior of the LLM
Real-ESRGAN with optional face correction and adjustable upscale
