Все модели

Animate Your Personalized Text-to-Image Diffusion Models (Long boot times!)

First version of a DadaNYC Lora based model

A FLUX model fine-tuned on images of the Utopian Scholastic aesthetic. Good at text too

Language-Free Training of a Text-to-Image Generator with CLIP

Flux lora, use "cassette futurism" to trigger generation

FacebookResearch/SeamlessM4T v2 - Massively Multilingual & Multimodal Machine Translation

Genetic algorithm like mixing of SDXL models

Segment Anything Model with point prompt.

Generates Images in the Big Medium Style

Exploratory SDXL fine-tuning on text "FOFR"

better at creating stickers

localfultonextractor's Erosumika 7B Mistral Merge, GGUF Q4_K_S-imat quantized by Lewdiculous.

Real Image Editing with DDPM Inversion and Semantic Guidance

NeverSleep's MiquMaid v2 2x70B Miqu-Mixtral MoE DPO Finetune, GGUF Q2_K quantized by NeverSleep.

Flux LoRA trained on generated images of random shapes

Inpaint anything with automatic mask generation

Translate text from one language to another with support for multiple text formats.

Fine-tuned for stylistic creativity.

Removes specified objects from image

Speech Enhancer

IMG2IMG for HiDream FULL AND DEV - does creative variations

3D models with texture fidelity and geometry precision

A fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. Piper is used in a variety of projects.

HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration

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

Unofficial Re-Trained AnimateAnyone (Image + DWPose Video → Animated Video of Image)

Flux lora, use "spitting image caricature" to trigger image generation

Flux LoRA, use 'DIXIT' to trigger generation, creates images with the art style of the board game DIXIT.

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

unet clothing segment

🎙️Hololive text-to-speech and voice-to-voice (Japanese🇯🇵 + English🇬🇧)

Generate art from text prompts. Based on kvfrans/clipdraw.

Image generation from Wav2CLIP through VQGAN-CLIP

Generate 5s and 10s videos in 720p resolution at 30fps

SDXL fine-tuned on film noir movie stills

Great image quality, good old SDXL with a new and improved Tile refiner.

Midsummer Blues-- trained on Midjourney --sref 2392289305

SDXL fine tuned on Genshin Impact landscape by imageapp.xyz

Empowering Code Large Language Models with Evol-Instruct

Optical character recognition to turn images of latex equations into latex format.