Make MS Paint images, a lora trained by aimingfail

Finte-tuned Stable Diffusion on high quality 3D images with a futuristic Sci-Fi theme

2B base version of Google’s Gemma model

Image generation, Inpaint Strength, loras custom_urls and enhancer.

Trained on generations with this melting green aesthetic cultivated using Stable Diffusion 2.1 ( Realism Engine) with themes from Aliens, Bollywood, Surrealism among many. WIP. Refer to Examples for trigger words

Age prediction using CLIP - Patched version of `https://replicate.com/andreasjansson/clip-age-predictor` that works with the new version of cog!

CodeLlama-34B-instruct with support for grammars and jsonschema

Stable Diffusion fine tuned on Midjourney v4 images.

multilingual-e5-large: A multi-language text embedding model

Control diffusion models

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

Kandinsky 2.2 Model (Text2Img, Img2Img and Inpainting)

RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting

Transfer the style of one image to another

Add colours to old images

The Yi series models are large language models trained from scratch by developers at 01.AI.

Monster Labs QrCode ControlNet on top of SD Realistic Vision v5.1

Generate a logo using text.

An Adversarial Approach for Picture Colorization

stable-diffusion with negative prompts, more scheduler