Brief-details: A LoRA model for FLUX.1-dev that generates 2.5D cartoon-style images with detailed parameters and specific training data, optimized for 768x1024 resolution.
Brief Details: A specialized LoRA model for Walking Dead-themed image generation, built on SDXL base 1.0. Features zombie and post-apocalyptic scene creation with 64 network dimensions.
Brief-details: A 123B parameter language model based on Largestral 2411, featuring system prompt support and creative capabilities with Metharme format compatibility
Brief Details: Lightweight 1B parameter instruction-tuned LLaMA model optimized for conversational AI and text generation with efficient resource usage
Brief Details: SmolVLM-Base is a compact 2.25B param multimodal model supporting image-text tasks with efficient architecture and BF16 precision.
Brief-details: A reward model based on Llama 3.1, part of the Tulu 3 family, focused on instruction following and performance optimization across diverse tasks.
Brief-details: A specialized LoRA model for FLUX.1-dev optimized for creating unique blend compositions with miniature figures, trained on 30 high-quality images using custom parameters.
Brief Details: StableV2V is an MIT-licensed video-to-video editing model focusing on shape consistency, combining multiple networks for enhanced stability and control.
Brief-details: Reducio-VAE is a powerful 3D VAE model for video compression, achieving 4096x downsampling while maintaining high quality through content-frame conditioning.
Brief Details: A powerful 15.2B parameter English-Korean Vision-Language Model with advanced grounding and OCR capabilities, built on Qwen2.5-14B-Instruct
Brief Details: A powerful 15.2B parameter English-Korean Vision-Language Model capable of multimodal tasks, OCR, and grounding, built on Qwen2.5-14B architecture.
Brief Details: A 12.2B parameter merged LLM combining 7 Mistral-based models, optimized for creative writing and worldbuilding with advanced prose capabilities.
Brief-details: A specialized LoRA model for FLUX.1-dev that generates Polaroid-style photo collages, trained on 24 images with specific focus on grid arrangements and artistic photography.
Brief-details: A 32.8B parameter fine-tuned Qwen2.5 model optimized for roleplay and creative writing, trained on diverse datasets with ChatML format
Brief Details: LLM2CLIP-Openai-L-14-336 is a 579M parameter vision-language model that enhances CLIP's capabilities through LLM integration, improving cross-modal tasks.
BRIEF-DETAILS: Lightweight CPU-optimized LLM using OpenVINO framework, supporting English & Russian text generation with 4-bit precision, ideal for Intel processors.
Brief-details: A specialized LoRA fine-tuning of FLUX.1-dev model focused on enhancing detail generation in images, using "Super Detail" trigger word with 64 network dimensions and trained on 15 images.
Brief Details: A 3B parameter LLaMA-based instruction-following model optimized for conversational AI and text generation, built on meta-llama/Llama-3.2-3B-Instruct architecture.
Brief Details: A 1.24B parameter lightweight conversational AI model based on Llama architecture, optimized for instruction-following and efficient text generation tasks.
Brief-details: 8B parameter instruction-following LLM built on Llama 3.1, optimized for diverse tasks including math and reasoning. Strong performance in safety and technical evaluations.
Brief-details: Artistic text-to-image LoRA model trained on FLUX.1-dev, specialized in creating nightmare-style artwork with 64 network dimensions and constant LR scheduler
