# LoRA adaptation

LoRA model fine-tuned based on FLUX.1-dev, capable of generating Ghibli-style vector images

A LoRA trained based on the Wan2.1 14B T2V model, capable of generating videos in a high-distortion micro planet fisheye style.

Latika9540 is a text-to-image generation model focused on creating sexy and beautiful images of Indian/Latina warrior women.

Granite-speech-3.2-8b is a compact and efficient speech language model specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).

A fine-tuned model based on Wan2.1 14B text-to-video foundation model, specialized for generating animal documentary-style video content

A LoRA-adapted vision-language model based on Llama-3.2-11B-Vision-Instruct, capable of transcribing Thai handwritten text from images.

A LoRA model fine-tuned based on the FLUX.1-dev foundation model for generating mspaint-style images

A LoRA model fine-tuned based on the FLUX.1-dev base model, specifically designed for generating 90s-style anime images.

This model specializes in generating visually striking images inspired by neon-decorated venues such as arcades and taverns.

LoRA model fine-tuned based on FLUX.1-dev foundation model, used for generating SRFNGV01 style illustration images

Flux latentpop is a LoRA model based on FLUX.1-dev, specializing in generating illustrations with a screen printing style and limited colors, particularly suitable for T-shirt designs and character portraits.

Eliminate the rejection response problem of the Llama-3.1-8B-Instruct model through LoRA technology

A DPO fine-tuned model based on Llama-3-8b, focused on enhancing truthfulness and mathematical reasoning capabilities

SDXS-512-Dreamshaper-Anime is an anime-style LoRA adaptation module based on SDXS-512-Dreamshaper, capable of generating high-resolution anime-style images in real-time from text prompts.

LoRA model based on Stable Diffusion v1.5 for text-to-image generation

This is a LoRA adaptation weight customized for the Stable Diffusion XL base model, trained via DreamBooth for generating images in specific styles.

This is a LoRA adapter designed for Stable Diffusion v1-5, reducing inference steps to just 2-8 steps, significantly improving generation speed.

m-ST5 is a multilingual sentence embedding model based on the mT5 encoder, specifically optimized for cross-lingual semantic textual similarity and sentence retrieval tasks.

This is the 8-bit quantized version of EleutherAI's GPT-J 6B parameter model, optimized for running and fine-tuning on limited GPU resources (e.g., Colab or 1080Ti).