Explore

I want to…

Upscale images

Upscaling models that create high-quality images from low-quality images

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Flux fine-tunes

Browse the diverse range of fine-tunes the community has custom-trained on Replicate

Make 3D stuff

Models that generate 3D objects, scenes, radiance fields, textures and multi-views.

Latest models

sdxl-1.0 finetuned with 'Bundaberg' bottle beverage images

Updated 207 runs

Implementation of SDXL RealVisXL_V1.0

Updated 44K runs

Creates Images Based on the 1930's US National Park Posters

Updated 486 runs

SDXL ControlNet - Depth

Updated 30K runs

Llama 2 13B fine-tuned on Bob Dylan lyrics

Updated 250 runs

Updated 67 runs

Determines the toxicity of text to image prompts, llama-13b fine-tune. [SAFETY_RANKING] between 0 (safe) and 10 (toxic)

Updated 1.9M runs

CLIP Interrogator (for faster inference)

Updated 119.8K runs

Updated 257 runs

Updated 72 runs

Updated 2K runs

An SDXL fine-tune based on Junji Ito's manga drawings

Updated 291 runs

Updated 132 runs

Updated 114 runs

Updated 44 runs

SDXL finetuned on fantasy TTRPG sourcebook art.

Updated 494 runs

Updated 207 runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 3.5K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 6.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.5K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 6.9K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 9K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 847 runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.1K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 5.1K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 58.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 9.7K runs

T4 GPU, negative embeddings,img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 9.4K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 21K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 6.9K runs

Updated 24 runs

The CLIP Interrogator is a prompt engineering tool that combines OpenAI's CLIP and Salesforce's BLIP to optimize text prompts to match a given image. Use the resulting prompts with text-to-image models like Stable Diffusion to create cool art!

Updated 2.7M runs

An SDXL fine-tune based on Tim Burton’s characters

Updated 422 runs

Updated 59 runs

360 Panorama SDXL image with inpainted wrapping seam

Updated 6.2K runs

An SDXL fine-tune based on Día de muertos’ catrina pictures

Updated 100 runs

Prokudin-Gorsky was a chemist and photographer, best known for his pioneering work in colour photography

Updated 238 runs

SDXL finetune to generate slick Icons and Flat Pop Constructivist Graphics with thick edges. Trained on Bing Generations

Updated 26.9K runs

Updated 388 runs

An SDXL fine-tune based on studio Ghibli picture stills

Updated 526 runs

An SDXL fine-tune based on Apple Emojis

Updated 7.3M runs

PyTorch version of Lightweight OpenPose as introduced in "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose"

Updated 1.6K runs

LLAMA-2 7b chat version by Meta. Stream support. Unaltered prompt. Temperature working properly. Economical hardware.

Updated 272 runs

Trained on https://www.zara.com/nl/nl/comfort-overhemd-met-structuur-p01063340.html?v1=301567503&v2=2297813

Updated 111 runs

Updated 563 runs

Generate images in the style of Vegetius, a writer of the Later Roman Empire. Start each prompt with: In the style of Vegetius, [your prompt]

Updated 143 runs

Updated 332 runs

Nougat: Neural Optical Understanding for Academic Documents

Updated 4.1K runs

Base version of Llama 2 13B, a 13 billion parameter language model

Updated 195.1K runs