# LoRA Fine-tuning

A ControlNet PEFT LoRA model based on PixArt-900M for image generation, supporting text-to-image and image-to-image conversion.

A Turkish law-specific language model based on Qwen3-14B, fine-tuned using the LoRA method and employing 4-bit quantization technology

LLaDA-8B-Tools Edition is a variant of the LLaDA-8B-Instruct model, specifically fine-tuned to enhance tool-calling capabilities, supporting functions like generating tool-call JSON and processing tool response data.

This is an image-to-image conversion model based on LoRA technology, primarily used for non-commercial image editing tasks.

LegoGPT is the first AI system that generates physically stable LEGO brick models from text prompts, fine-tuned based on Llama-3.2-1B-Instruct.

LoRA fine-tuned model based on flux learning, specifically imitating Winslow Homer's artistic style

A training model based on flux learning, capable of generating oil paintings in the style of Paul Cezanne

A fine-tuned version based on the Qwen2.5-3B-Instruct model on medical and health datasets, designed to generate medical-related responses and provide health guidance to users.

This is a LoRA adapter trained for the FLUX.1-dev text-to-image model, supporting invocation via diffusers or ComfyUI to generate images of specific styles.

CropSeek-LLM is a fine-tuned language model specifically designed for crop optimization decision support. Based on the DeepSeek-R1 architecture, it excels in answering agricultural domain questions such as crop cultivation, soil conditions, and pest control.

This is a text-to-image generation model fine-tuned based on the FLUX.1-dev base model, specializing in architectural image generation.

This model is a fine-tuned version optimized from Mistral-7B-Instruct-v0.3, specifically designed for Q&A tasks in the field of forensic investigations, supporting advanced forensic reasoning and rapid knowledge retrieval.

PPACE is an 8-billion-parameter large language model specifically designed for automatic classification of biomedical funding project abstracts, supporting the World Health Organization's research priority classification.

A model fine-tuned based on LLama3-8B-instruct, specifically designed for the WASSA2024 empathy detection task

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

This is a DreamBooth LoRA model based on HiDream-ai/HiDream-I1-Full, specializing in generating yarn art-style dog images.

This is a LoRA adapter trained for the FLUX.1-dev text-to-image model, designed to generate images of a specific style.

A merged model based on Meta-Llama-3.1-8B-Instruct, fine-tuned for legal summarization tasks, capable of converting legal terminology into concise and understandable summaries.

A LoRA diffusion model fine-tuned on the FLUX.1-dev base model for text-to-image conversion with SLUSHWAVE style

This is a LoRA adapter specifically designed for the FLUX.1-dev text-to-image generation 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 TinyLlama fine-tuned model for generating survey responses, optimized for cross-domain synthetic response generation

An image editing fine-tuned control LoRA based on THUDM/CogView4-6B model, supporting style transfer and content editing through text instructions

A text-to-image generation model based on black-forest-labs/FLUX.1-dev foundation model, fine-tuned using Low-Rank Adaptation (LoRA) technology

This is a LoRA fine-tuned model based on FLUX.1-dev, specifically designed for generating images in children's book style.

A LoRA model trained on the FLUX.1-dev base model, specifically designed for generating street art-style images.

LoRA trained based on the Wan2.1 14B I2V 480p model, specifically designed for generating videos of characters crying

LoRA trained on the Wan2.1 14B I2V 480p model for generating kissing interaction videos from images

LoRA trained on the Wan2.1 14B I2V 480p model for generating angry expression video conversions

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

LoRA trained on the Wan2.1 14B T2V model, specializing in generating various creative tornado videos

A LoRA trained on the Wan2.1 14B T2V model, specifically designed for generating video content of abandoned places.

A realistic style image generation model based on LoRA technology, optimized for the FLUX.1-dev base model

A dialogue model fine-tuned and optimized based on microsoft/phi-3-mini-4k-instruct, specifically designed for role-playing scenarios, requiring specific prompt formats for optimal results

This is a LoRA-based text-to-image diffusion model specifically designed for generating 3D-style station cartoon character images.

This is a LoRA-based text-to-image diffusion model specifically designed to generate images with an oil skin effect.

LoRA trained on the Wan2.1 14B I2V 480p model, capable of transforming any person/object in an image into an assassin-style dynamic video

LoRA trained on Wan2.1 14B I2V 480p model that transforms any person/object in images into zen versions and generates videos.

A LoRA model trained on Wan2.1 14B I2V 480p, capable of transforming any person/object in an image into a pirate captain version.

LoRA trained on Wan2.1 14B I2V 480p model, capable of transforming any person/object in an image into a princess version