# Diffusion Model Optimization

Karmix-XL-v0 is a diffusion model-based text-to-image generation model that supports English input.

This is a LoRA adapter trained for the FLUX.1-dev text-to-image model, compatible with diffusers or ComfyUI.

A LoRA model optimized based on AnimagineXL 4.0, specifically designed for generating anime character images in PVC figure style

A text-to-image diffusion model based on LoRA technology, using 'HannahOwO' as a trigger word to generate character images of a specific style.

Flux-Surreal-Style-2 is a text-to-image diffusion model based on LoRA technology, capable of generating images with a surrealist style.

A text-to-image model trained on a small-scale curated dataset through strategic data augmentation methods, significantly improving generation quality

XPEN is a text-to-image generation model based on diffusion models and LoRA technology

LoRA fine-tuned model based on FLUX.1-dev, specializing in text-to-image generation tasks with Midjourney style integration

A text-to-image generation model based on the FLUX.1-dev foundation model, specifically designed for generating portrait images of Lindsay Lohan in her present-day appearance.

A text-to-image diffusion model based on LoRA technology, specializing in generating isometric architectural scene images.

A LoRA model based on 3DXL technology, specializing in generating high-quality 3D-rendered character images

This is a text-to-image model based on LoRA technology, specifically designed for generating movie board style black-and-white or monochrome poster images.

This is a LoRA diffusion model based on the Raelina/Raehoshi-illust-XL base model, focusing on text-to-image generation tasks.

An anime-style text-to-image diffusion model based on LoRA technology, using FLUX.1-dev as the base model

This is a text-to-image diffusion model based on LoRA technology, specifically designed to generate photos with the shooting style of iPhone15.

This is a LoRA weight model trained for THUDM/CogVideoX-2b, focusing on the text-to-video generation task.

FluxteusV1 is a text-to-image diffusion model based on the FLUX.1-dev foundation model, trained by integrating over 25 LoRA models, offering diverse stylistic expressiveness.

A LoRA model trained based on Ghibli's retro anime style for generating anime images with unique aesthetics.

Tango 2 is an improved text-to-audio generation model based on Tango, achieving alignment training for audio generation through Direct Preference Optimization (DPO) technology

This model is a text-to-image generation model based on stable diffusion technology, primarily used to generate high-quality artistic images from text prompts.

An AI focused on AI art image generation, developed with approximately 7,000 GPU hours, based on the Stable Diffusion architecture