flux2-dev-gguf is an image-to-image conversion model based on FLUX.2-dev, specifically designed to generate images in a specific style based on text prompts. This model supports running in the ComfyUI environment and can convert text descriptions into stylized visual content.

MultimodalGgufEnglish

SAM 3 is the third-generation promptable segmentation foundation model launched by Meta, which uniformly supports image and video segmentation tasks. Compared with its predecessor SAM 2, it introduces the ability of open vocabulary concept segmentation, can handle a large number of text prompts, and achieves 75-80% of human performance in the SA-CO benchmark test.

Computer VisionTransformersEnglish

SAM3 is a concept-based arbitrary segmentation model that can generate precise image segmentation masks based on input prompt information such as points and boxes. This version is the ONNX format of the SAM3 tracker model, which can run efficiently in the browser environment through the Transformers.js library.

Computer VisionTransformers

Stable Diffusion v2-1-base is a diffusion model for text-to-image generation, which has been fine-tuned with an additional 220k steps based on v2-base. This model can generate and modify images according to text prompts, support multiple resolution outputs, and is suitable for various fields such as artistic creation and educational research.

Computer VisionDiffusers

Stable Diffusion v2 is a text-to-image generation model based on the diffusion model, capable of generating and modifying images according to text prompts. This model is trained on a subset of the LAION-5B dataset, combining an autoencoder and a diffusion model, and is trained in the latent space, supporting multiple resolutions and tasks.

Computer VisionDiffusers

Stable Diffusion v2-1-unclip is a diffusion model fine-tuned based on Stable Diffusion 2.1. It can accept text prompts and CLIP image embeddings, and is used to create image variants or be used in combination with the text-to-image CLIP prior.

MultimodalDiffusers

SAM 3 is the third - generation promptable segmentation foundation model launched by Meta. It can use text or visual prompts (points, boxes, masks) to detect, segment, and track objects in images and videos. Compared with previous generations, SAM 3 introduces the ability to exhaustively segment all instances of open - vocabulary concepts, supports a large number of open - vocabulary prompts, and achieves 75 - 80% of human performance on the SA - CO benchmark.

Computer VisionTransformersEnglish

This is a statically quantized version of the gravitee-io/very-small-prompt-compression model, specifically designed for prompt compression and text summarization tasks. The model is trained on the Dolly-15k prompt compression dataset and supports English language processing, offering multiple quantization levels to choose from.

Natural Language ProcessingTransformersEnglish

This is an efficient text summarization model specifically designed to compress text content in large language model prompts, achieving a compression ratio of over 7 times and significantly reducing API call costs.

Natural Language ProcessingTransformersEnglish

This is the MXFP4_MOE quantized version of the PromptCoT-2.0-SelfPlay-30B-A3B model, specifically designed for text generation tasks. The model adopts chain of thought prompting and self-play training techniques, and achieves more efficient inference performance through quantization optimization.

Natural Language ProcessingGguf

This is a sequence-to-sequence model specifically designed to compress short user prompts (≤64 tokens) and can achieve low-latency operation of less than 100 milliseconds on modern GPUs. It serves as a lightweight preprocessing stage to support high-capacity large language models.

Natural Language ProcessingTransformers

This is a LyCORIS adapter based on the Qwen/Qwen-Image model, specifically designed for text-to-image and image-to-image generation tasks. The model did not use validation prompts during training and adopted optimized training configurations and quantization techniques.

MultimodalDiffusers

LibreFLUX-ControlNet is a text-to-image generation model based on the ControlNet architecture, using LibreFLUX as the base Transformer model. This model is trained on the SA1B dataset and can generate high-quality image content based on text prompts and control images.

Computer VisionDiffusers

This is the first - generation powerful vibe - code large language model, optimized to directly generate natural language and code completion based on loosely structured 'atmosphere coding' prompts. Compared with early models, it has lower prompt engineering overhead, smoother latent space interpolation, and is easier to guide the generation of usable code.

Natural Language ProcessingTransformersEnglish

The GA Guard series is an open-source weight review model designed to help developers and organizations maintain the security, compliance, and consistency of language models with the real world. This model can detect seven violation categories, including illegal activities, hate and abuse, personal identity information and intellectual property, prompt security, pornographic content, false information, and violence and self-harm.

Natural Language ProcessingTransformersEnglish

ModernBERT PromptGuard is a high-performance binary classifier specifically designed to detect malicious prompts in large language model applications, including prompt injection and jailbreak attacks.

Natural Language ProcessingTransformersEnglish

Qwen3-4B-SafeRL is a safety-aligned version of the Qwen3-4B model. It enhances the model's robustness against harmful or adversarial prompts through reinforcement learning training. This version uses a hybrid reward function for optimization, balancing three objectives: safety, usefulness, and minimizing unnecessary rejections.

Natural Language ProcessingTransformersEnglish

Mira is a text generation model based on the fusion of multiple Gemma 3 27B base models. Through carefully selected training data and specific training methods, it has a unique ability to generate poetic texts. This model performs excellently in role-playing and creative writing, and can generate texts with literary charm according to different system prompts.

Natural Language ProcessingTransformers

Qwen3-4B-SafeRL is a safety-aligned version based on the Qwen3-4B model. It is trained through reinforcement learning and combined with the reward signals of Qwen3Guard-Gen, enhancing the model's robustness against harmful or adversarial prompts. While ensuring safety, it avoids overly simple or evasive rejection behaviors.

Natural Language ProcessingTransformers

A text-to-image generation model based on sdxl-turbo and processed by Nunchaku quantization, aiming to generate high-quality images according to text prompts. This model is optimized for efficient inference, significantly reducing the model size while maintaining performance.

Computer VisionDiffusersEnglish