This is a fine-tuned version based on Qwen/Qwen3-8B-Base, trained using the TRL framework and the GKD (On-Policy Distillation) method, specifically designed for text generation tasks. The model learns by self-generating errors, improving the quality and stability of text generation.

Natural Language ProcessingTransformers

simpletuner-lora is a LyCORIS adapter based on stabilityai/stable-diffusion-3.5-medium, specifically designed for image generation tasks such as text-to-image. This model is implemented through LoRA fine-tuning technology and is mainly trained using the validation prompt 'A photo-realistic image of a cat'.

Computer VisionDiffusers

This is a LyCORIS adapter based on stabilityai/stable-diffusion-3.5-large, specifically designed for text-to-image generation. It can generate high-quality product photography images based on text descriptions and is specially optimized for Borges brand products.

Computer VisionDiffusers

simpletuner-lora is a LoRA fine-tuning model based on PEFT, derived from stabilityai/stable-diffusion-3.5-large, specifically designed for text-to-image and image-to-image conversion tasks. This model has been trained for 162 epochs, featuring efficient inference capabilities and good image generation quality.

MultimodalDiffusers

The embeddings project is a text-to-image conversion model based on LoRA and Diffusers technology. It uses stabilityai/stable-diffusion-3.5-large as the base model and provides a diffusion LoRA template, which can generate high-quality images based on specific models.

MultimodalDiffusers

A losslessly compressed version of stabilityai/stable-diffusion-3.5-large using DFloat11 format, reducing size by 30% while maintaining 100% accuracy

Computer VisionDiffusers

A diffusion model that generates up to 11 seconds of 44.1kHz stereo audio based on text prompts

Audio ProcessingSafetensorsEnglish

A fusion result of multiple 12B parameter models, optimized for roleplay with both creativity and stability, supporting 16k long context

Natural Language ProcessingTransformersMultiple Languages

Based on the fusion of multiple pre-trained language models, version V.5 has improved stability and content performance

Natural Language ProcessingTransformers

GodSlayer-12B-ABYSS is a 12B-parameter model obtained by merging multiple pre-trained language models through mergekit, designed to reduce positivity bias while maintaining stability and coherence, and to enhance realism and diversified response capabilities.

Natural Language ProcessingTransformers

A text-to-image diffusion model developed by Stability AI, featuring dual text encoders and latent diffusion technology, which can be used independently or with optimization modules for enhanced results

Computer VisionDiffusers

A full-rank fine-tuned model based on stabilityai/stable-diffusion-3.5-medium, focusing on text-to-image and image-to-image generation tasks.

Computer VisionDiffusers

An 8B-parameter model based on Llama 3.1, supporting 1 million token context length, optimized for creative writing and role-playing with high stability and low perplexity characteristics.

Natural Language ProcessingGgufEnglish

LyCORIS adapter based on stabilityai/stable-diffusion-3.5-large, focused on text-to-image and image-to-image tasks

Computer VisionDiffusers

A ControlNet PEFT LoHa model based on stabilityai/stable-diffusion-xl-base-1.0, mainly used for generating realistic cat photos.

Computer VisionDiffusers

A LoRA model trained on stabilityai/stable-diffusion-3.5-large, specifically designed for generating images suitable for screen printing processes.

Computer VisionDiffusers

This is a LoRA-adapted weight model based on stabilityai/stable-diffusion-xl-base-1.0, obtained through DreamBooth training, focusing on generating images of specific characters.

Computer VisionDiffusers

This is an autoencoder fine-tuned from StabilityAI's SDXL-VAE model, focusing on image reconstruction tasks.

Computer VisionDiffusersEnglish

TripoSR is a fast feed-forward 3D generation model developed collaboratively by Stability AI and Tripo AI, capable of rapidly generating 3D models from a single image.

Violet-Lyra-Gutenberg-v2-12b is a large language model with 12B parameters created through model merging technology. Based on the Mistral-Nemo-Base-2407 base model, it integrates the advantages of multiple excellent models. This model shows outstanding performance in terms of stability and has achieved amazing results on the UGI leaderboard, with excellent intelligent performance.

Natural Language ProcessingTransformers