# LoRA Fine-Tuning

A multilingual text-to-speech model fine-tuned based on Orpheus-3b, optimized for African low-resource languages, supporting voice cloning and emotion synthesis

LoRA model based on stable-diffusion-3.5-medium, focused on high-quality image generation

LoRA weights trained for THUDM/CogVideoX-5b-I2V, designed for image-to-video tasks

LyCORIS adapter based on Stable Diffusion XL 1.0, focused on image generation tasks

A high-quality foundational LoRA model specifically designed for Stable Diffusion, capable of generating surreal images with extraordinary detail, realistic textures, and natural lighting.

This model is the result of merging the base model DeepSeek-R1-distilled-Qwen-32B with the approval_bureau_model_lora adapter, suitable for document review, text generation, and content approval-related scenarios.

Functional LoRA trained based on FLUX.1-dev to achieve deep depth of field (anti-blur) effects

A LoRA adapter based on the Wan2.1-T2V-14B text-to-video model, specifically designed for generating video content in the style of ancient book illustrations

A LoRA trained on the Wan2.1 14B I2V 480p model, specifically designed for generating explosion effects videos, suitable for image-to-video and text-to-video tasks.

LeX-Enhancer is a lightweight prompt enhancement model distilled from DeepSeek-R1, designed to generate high-quality, visually rich prompt outputs suitable for text-to-image generation.

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

This is a PEFT LoRA based on the FLUX.1-dev model, specifically designed for generating logos for racing game applications.

A financial chain-of-thought reasoning model fine-tuned based on DeepSeek-R1-Distill-Llama-8B, specializing in financial domain problem analysis and solutions.

This is a diffusion model fine-tuned with LoRA, capable of generating portrait photos in Anya Taylor-Joy's 2017 style.

A LoRA model trained on the Flex.1-alpha base model, specializing in generating magnificent natural landscape images, particularly excelling in sunset mountain scenes

This is a PEFT LoRA model based on the FLUX.1-dev model, focusing on text-to-image and image-to-image tasks, supporting high-resolution image generation.

A LoRA fine-tuning model customized for FLUX.1 [Developer Edition], specializing in generating seasonal landscapes, vegetation, and natural environments with a focus on autumn scenes.

FLUX.1-dev is a LoRA-based text-to-image generation model, specializing in pixel art style images, particularly suitable for game asset creation.

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

A functional LoRA trained on FLUX.1-dev for achieving deep depth of field (anti-blur) effects

This is a text-to-image generation model combining Hands XL, SD 1.5, and FLUX.1-dev technologies, focusing on high-quality image generation.

A text-to-image generation model trained on public domain vintage advertisements, capable of generating retro-style ad images based on text prompts.

A model capable of generating lively anime-style illustrations with special effect details, especially suitable for fantasy themes.

A LLaVA model fine-tuned based on Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336, supporting image-text-to-text tasks

Jamba-Hercules is a fine-tuned large language model based on ai21labs/Jamba-v0.1, trained using the Locutusque/hercules-v4.0 dataset, focusing on text generation tasks.

A TCD LoRA model based on Stable Diffusion v1.5, optimized for image generation efficiency through Trajectory Consistency Distillation technology.

This model is a large language model merged from Intel's neural-chat-7b-v3-1 and PulsarAI's Nebula-v2-7B-Lora.

A distilled consistency adapter designed for segmind/SSD-1B, reducing inference steps to just 2-8 steps

Dynamic LoRAs model that adds specific types of motion effects to animations

A LoRA fine-tuned model based on Stable Diffusion XL, specifically designed for generating ASCII art-style images.

This is a LoRA designed for the SDXL 1.0 base model, used to generate images of Ugly Sonic.