fofr / realistic-vision-hyper

Turn a face into 3D, emoji, pixel art, video game, claymation or toy

An SDXL fine-tune based on Apple Emojis

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

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

Turn a face into a sticker

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

Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet

Make stickers with AI. Generates graphics with transparent backgrounds.

Create images of a given character in different poses

A flux lora fine-tuned on black light images

Transfer the style of one image to another

Amazing photorealism with RealVisXL_V3.0, based on SDXL, trainable

Adapt any picture of a face into another image

Create a waveform video from audio

Multi-controlnet, lora loading, img2img, inpainting

Use a face to make images. Uses SDXL fine-tuned checkpoints.

Fast and high quality lightning model, epiCRealismXL-Lightning Hades

Use a face to instantly make images. Uses SDXL Lightning checkpoints.

Portrait animation using a driving video source

Quickly edit the expression of a face

An SDXL fine-tuned on Dalle3 underwater imagery

Generate image prompts for Midjourney. Prefix inputs with "Image: "

SDXL fine-tuned on photos of freshly inked tattoos

Create videos from illustrated input images

Create illusions with img2img and masking support

A fine-tuned SDXL lora based on the Barbie movie

Canny, soft edge, depth, lineart, segmentation, pose, etc

A model for experimenting with all the SD3 settings. Non-commercial use only, unless you have a Stability AI Self Hosted License.

Fast animation using a latent consistency model

A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team

Stable Diffusion 3 medium with added variability in outputs. Non-commercial use only, unless you have a Stability AI Self Hosted License.

Kolors with style transfer, composition transfer and other IPAdapter techniques

SDXL fine-tuned on MJv6 Simpsons generated images

FLUX.1-dev with XLabs-AI’s realism lora

LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched.

Generate a video that morphs between subjects, with an optional style

Run any ComfyUI workflow on an A100. Guide: https://github.com/fofr/cog-comfyui

Split a video into frames

An SDXL fine-tune based on bad 2004 digital photography

A fine-tuned SDXL lora based on Tron Legacy

Many models: RealVisXL, Juggernaut, Proteus, DreamShaper, etc.

Run Wan2.1 14b or 1.3b with a lora

Explore how Flux Dev responds when you change the strengths of layers in the model. See readme for examples of how to select layers.

Ultra high resolution images (up to 4096x4096) based on Stable Cascade

Largest completely open sourced flow-based generation model that is capable of text-to-image generation

SDXL LCM with multi-controlnet, lora loading, img2img, inpainting

A cinematic model fine-tuned on SDXL

Merge two images, with an optional third for controlnet.

Merge two images together with a prompt

An SDXL fine-tune on Apple Vision Pro

Video toolkit – convert, make GIFs, extract audio

Uses 'Align your steps' for faster higher quality images

MusicGen fine-tuned on chamber choir music

An SDXL fine-tune for solid color images

A flux lora trained on a 1980s cyberpunk aesthetic

SDXL fine-tuned on black light imagery

Flux lora trained on Midjourney v3 outputs from 2022, use "a dream, in the style of MJV3" to trigger generation, also try increasing lora strength above 1

Flux lora, use "MNCRFTMOV" to trigger image generation

ZavyChromaXL v7, a high contrast and colorful SDXL fine-tune

Flux lora, use "CLR" to trigger image generation

A realistic, high quality 5 step lightning model

Flux lora, use the term "MNALSA" to trigger generation

SDXL fine-tuned on the people in Toy Story (1995)

Fast video2video with a latent consistency model

SDXL fine-tuned on both Barbie and Tron Legacy

Make pictures of an AI character named 0_1.webp

Flux lora, fine tuned on NEO-1X robot, use "NEO1X" to trigger image generation

Convert a set of frames to a video

SDXL fine-tuned on energy drink designs

A flux dev lora fine-tuned on bad 2004 digital photography

A flux lora fine-tuned to produce handwritten text

SDXL fine-tune of Star Trek Next Generation interiors

An SDXL fine-tune based on Deep Dream

SDXL fine-tune based on illustrated cross sections

SDXL fine-tuned on Pixar Cars

Make MS Paint images, a lora trained by aimingfail

A wrapper model for captioning multiple images using GPT, Claude or Gemini, useful for lora training

👀 SDXL fine-tune to add googly eyes to anything

SDXL fine-tuned on pareidolia

Exploratory SDXL fine-tuning on text "FOFR"

Flux fine-tuned on JWST deep space astrophotography

A flux fine-tune based on neo-impressionism

SDXL fine-tuned on Santa Hats

Flux lora by AggravatingScree7189, use "cyberpunk typeface" to trigger image generation

An SDXL fine-tune based on the Labyrinth movie

Flux lora, use "XSEC cross section" to trigger image generation

Flux lora, use "cassette futurism" to trigger generation

Flux dev lora trained on photos of 1970s food

Tshirt designs with a hidden Replicate logo

Flux lora, trained on macro textures, use "MCROTX" to trigger image generation

Flux lora, use “WRNG” to trigger image generation

An SDXL fine-tune on bad 2048x2048 images

Generate music with YuE-s1-7B (English, chain of thought model)

SDXL fine-tuned on Xmas sweaters