Все модели

Image similarity metric that that compares a reference image to a set of images.

Hunyuan-Video model finetuned on The Grand Budapest Hotel (2014). Trigger word is "THGRN". Use "A video in the style of THGRN, THGRN" at the beginning of your prompt for best results.

Detect whether a GitHub user has a custom or default avatar

Terminus XL Gamma is a new state-of-the-art latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

Flux lora, use "CYBERCAB" to trigger generations

A fine-tuned SDXL model based on the movie Dune.

SDXL finetune (IIRC?) based on the Adventure Time show

Inpaint a selected area of an image using controlnet union for SDXL.

Generate Factorio-themed item icons

Remove any object from video - fast.

xl

Flux fine-tuned on art of ruin

A Flux LoRA trained on photos of Jake's dog: Queso

Generates ryanpollocks

Create images with a retro sci fi style

MiniCPM-V 4.0 has strong image and video understanding performance

Hunyuan-Video model finetuned on Cowboy Bebop (1998). Trigger word is "CWBYB". Use "A video in the style of CWBYB, CWBYB" at the beginning of your prompt for best results.

Model generuje obrazki podobne do Gwarków olkuskich. Wytrenowany na bardzo małym zbiorze danych.

Stability AI's FreeWilly2

My own personal copy of daanelson/whisperx

LUSTERBINDS Creatures of lust, luster and artifice. Project: The Model is the Message. To trigger the modeled construct use lusterbinds_1 as a token.

Tiny vision language model

Hip segmentation from the X-ray image

PyTSMod is an open-source library for Time-Scale Modification(eg. time-stretching) algorithms, by Sangeon Yong at MAC Lab, KAIST.

Generate photos like old school US National Park Posters

Use a subset of https://github.com/barun-saha/slide-deck-ai to create powerpoint slides from a json description - using python-pptx (https://github.com/scanny/python-pptx)

An actors headshot creator based on the style of professional photographer Daniel Spencer

Yi-VL-34B is the first open-source 34B VL model worldwide. It demonstrates exceptional performance, ranking first among all existing open-source models in the latest benchmarks including MMMU and CMMMU.

Sketch2Image

A fine-tuned SDXL lora based on the Obama hope poster

Detecting Twenty-thousand Classes using Image-level Supervision

👻

test api

SDXL model trained on the game The Return of The Obra Dinn

Tesla Model 3 Highland SDXL fine-tune

Generate music based on the Monkey Island theme using the FIGARO model

Hunyuan-Video model finetuned on Spider-Man: Into the Spider-Verse (2018). Trigger word is "SPDRM". Use "A video in the style of SPDRM, SPDRM" at the beginning of your prompt for best results.