Brief Details: A powerful 12.2B parameter language model combining multiple Mistral-based models, optimized for creative writing and worldbuilding with enhanced prose capabilities.
Brief Details: LLM2CLIP model that extends CLIP capabilities using LLMs, featuring 579M params and specialized for zero-shot classification and cross-modal tasks.
BRIEF-DETAILS: Tulu-3 8B: Advanced instruction-following LLM built on Llama 3.1, optimized for math, reasoning & safe outputs. Strong performance on GSM8K & MATH benchmarks.
Brief-details: A LoRA model fine-tuned on FLUX.1-dev for DALL-E style image generation, featuring high-resolution outputs with 64 network dimensions and 32 alpha settings. Optimized for photorealistic and artistic renders.
BRIEF DETAILS: A high-performance text-to-image model combining Flux.1 variants, optimized for 4-8 step generation with enhanced prompt following and detailed output generation at 11.9B parameters.
Brief-details: Ovis1.6-Gemma2-9B is a 10.2B parameter multimodal LLM that leads OpenCompass benchmark for models under 30B params, featuring Gemma architecture and SigLIP visual processing.
Brief Details: AIMv2-huge is a 681M parameter vision model from Apple, achieving 87.5% ImageNet accuracy with strong multimodal capabilities and feature extraction performance.
Brief Details: Florence-2-base-PromptGen-v2.0 is a lightweight 271M parameter image captioning model offering multiple caption styles with minimal VRAM usage (1GB) and fast processing.
Brief Details: LLM2CLIP-EVA02-L-14-336 is a zero-shot image classification model that leverages LLMs to enhance CLIP's capabilities, offering improved cross-modal and multilingual performance.
Brief Details: A specialized LoRA model for clothing image generation, built on FLUX.1-dev base model with Florence-2-large captioning. Optimized for detailed clothing renders with 64 network dimensions.
Brief-details: A specialized LoRA model for FLUX.1-dev that generates 2.5D toon-style images with 64 network dimensions and 32 alpha, optimized for 768x1024 resolution.
Brief Details: A Walking Dead-themed LoRA model for Stable Diffusion XL, specialized in generating apocalyptic and zombie-related imagery with 64 network dimensions and AdamW optimization.
Brief-details: A powerful 123B parameter language model offering multiple GGUF quantizations for efficient deployment, supporting 10 languages and optimized for research use
BRIEF DETAILS: A 12.2B parameter Mistral-based merge combining 7 models optimized for creative writing and worldbuilding, using DARE-TIES methodology.
Brief-details: LLM2CLIP-Openai-L-14-336 is a 579M parameter vision foundation model that extends CLIP's capabilities through LLM integration, enabling better cross-modal understanding.
Brief-details: FLUX.1-Fill-dev-gguf is an 11.9B parameter GGUF-converted image generation model optimized for ComfyUI integration, featuring quantized architecture for efficient deployment.
Brief Details: Marco-o1-GGUF is a 7.62B parameter model optimized for both structured (math, physics, coding) and creative tasks, available in multiple GGUF quantizations.
Brief-details: Text-to-image diffusion model with 11.9B params, optimized for 4-step generation. Apache 2.0 licensed, offers high-quality image creation with enhanced typography and complex prompt handling.
Brief Details: Tulu-3 8B is an advanced instruction-following LLM built on Llama 3.1, optimized for math, reasoning, and chat tasks with 8B parameters.
Brief Details: A 500M parameter multilingual text-to-speech model supporting English, Chinese, Japanese, and Korean, with advanced voice cloning capabilities and GGUF optimization for efficient inference.
BRIEF DETAILS: A specialized LoRA model for SDXL that transforms images into pencil art and line drawings, featuring clean black and white sketches with support for detailed coloring book-style outputs.
