Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 21

  • SmolVLM2-256M-Video-Instruct↗

    HuggingFaceTB

    SmolVLM2-256M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.38GB of GPU RAM for video inference. This efficiency makes it particularly well-suited for on-device applications that require specific domain fine-tuning and computational resources may be limited. - **Developed by:** Hugging Face 🤗 - **Model type:** Multi-modal model (image/multi-image/video/text) - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Architecture:** Based on Idefics3 (see technical summary) - **Demo:** Video Highlight Generator - **Blog:** Blog post

  • CommunityForensics-DeepfakeDet-ViT↗

    buildborderless

    Vision Transformer (ViT-Small) trained on 2.7M samples across 4,803 generators for detecting AI-generated images. Presented in Community Forensics: Using Thousands of Generators to Train Fake Image Detectors (CVPR 2025). **Uploaded for community validation as part of OpenSight** — An upcoming open-source framework for adaptive deepfake detection. **Project OpenSight HF Spaces coming soon with an eval playground and eventually a leaderboard. Preview:**

  • pornworks-real-porn-photo-realistic-nsfw-sdxl-and-pony-chekpoint↗

    Manjushri

    The latest version of the model is always available online at PornWorks.com - best nsfw neural generator We have done a lot of work to create a model that follows the hint perfectly, producing the highest quality NSFW output images even without using ADetailer and Upscaler

  • Imager-1↗

    Imagers

    **Imager-1** is an AI model designed to detect AI-generated images with high precision; it can detect DALL-E 2. We will soon launch **imager-1-small** and **imager-2**, which will be able to detect DALL-E 3 and other text-to-image models. This repository contains the **base model** of Imager-1, released for **developers and researchers** who want direct access to the architecture, weights, and training pipeline. Imager always publishes a **separately verified and production-ready version** of each model, tested against real-world generators before release. This base model is provided so the community can build on top of it, fine-tune it, or integrate it into their own systems.

  • marigold-depth-v1-1↗

    prs-eth

    This is a model card for the `marigold-depth-v1-1` model for monocular depth estimation from a single image. The model is fine-tuned from the `stable-diffusion-2` model as described in our papers: - CVPR'2024 paper titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation" - Journal extension titled "Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis"

  • marigold-iid-lighting-v1-1↗

    prs-eth

    This is a model card for the `marigold-iid-lighting-v1-1` model for single-image Intrinsic Image Decomposition (IID). The model is fine-tuned from the `stable-diffusion-2` model as described in our papers: - CVPR'2024 paper titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation" - Journal extension titled "Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis" This model type (`lighting`) is trained to perform HyperSim decomposition into **Albedo**, **Diffuse shading**, and **Non-diffuse residual**. This decomposition aligns with the intrinsic residual model \\(I = A*S+R\\), where the image \\(I\\) is composed of a three-channel albedo \\(A\\), a three-channel diffuse shading component \\(S\\) (representing illumination color), and an additive three-channel residual term \\(R\\) capturing non-diffuse effects. The input is in the sRGB color space, while all outputs are in linear space. For an alternative model type (`appearance`) that performs decomposition into Albedo, Roughness, and Metallicity, click here.

  • BAGEL-7B-MoT↗

    字节跳动

    > We present **BAGEL**, an open‑source multimodal foundation model with 7B active parameters (14B total) trained on large‑scale interleaved multimodal data. BAGEL outperforms the current top‑tier open‑source VLMs like Qwen2.5-VL and InternVL-2.5 on standard multimodal understanding leaderboards, and delivers text‑to‑image quality that is competitive with strong specialist generators such as SD3. Moreover, BAGEL demonstrates superior qualitative results in classical image‑editing scenarios than the leading open-source models. More importantly, it extends to free-form visual manipulation, multiview synthesis, and world navigation, capabilities that constitute "world-modeling" tasks beyond the scope of previous image-editing models. This repository hosts the model weights for **BAGEL**. For installation, usage instructions, and further documentation, please visit our GitHub repository. BAGEL adopts a Mixture-of-Transformer-Experts (MoT) architecture to maximize the model’s capacity to learn from richly diverse multimodal information. Following the same principle of capacity maximization, it utilizes two separate encoders to capture pixel-level and semantic-level features of an image. The overall framework follows a Next Group of Token Prediction paradigm, where the model is trained to predict the next group of language or visual tokens as a compression target.

  • Qwen-Image-2.1-PE-T2I-GGUF↗

    prithivMLmods

    > **Qwen-Image-2.1-PE-T2I** is the text-to-image prompt-rewriting model for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL-9B that turns a brief image request in any language into a detailed, expanded English prompt paired with a recommended aspect ratio, acting as the bridge between casual multilingual user requests (e.g., a short Chinese phrase describing a corgi playing guitar in the rain) and the precise, richly-detailed instructions the downstream 7B-parameter DiT-based Qwen-Image-2.1 generator needs for best results. After a ` ` reasoning block, it outputs a structured JSON object containing the `rewritten_prompt` and a `wh_ratio` value (e.g., `16:9`), which maps directly to standard render resolutions when passed into the Diffusers `QwenImage21Pipeline`. It's usable via standard Hugging Face `AutoModelForCausalLM` loading, is intended purely as a preprocessing step ahead of image generation rather than a general-purpose chat model, and is released under the Qwen Research License Agreement. > [!NOTE] System Prompt — https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I/blob/main/system_prompt.txt File Name | Quant Type | File Size | File Link | |-----------|------------|-----------|-----------| | Qwen-Image-2.1-PE-T2I.BF16.gguf | BF16 | 17.9 GB | Download | | Qwen-Image-2.1-PE-T2I.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Download | | Qwen-Image-2.1-PE-T2I.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Download | | Qwen-Image-2.1-PE-T2I.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Download | | Qwen-Image-2.1-PE-T2I.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Download | | Qwen-Image-2.1-PE-T2I.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Download | | Qwen-Image-2.1-PE-T2I.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Download |

  • DMAD↗

    ZhengmingYu

    This repository holds the DMAD students of the paper: 4-step students of **MiniMax-H3** (33B, text-to-audio-video) and of **Wan2.1-T2V** (1.3B and 14B), 4- and 1-step students of **SDXL**, and 1-step students of the **EDM ImageNet-64** teacher. The inference and training code is in the code repository (`train/h3`, `train/wan`, `train/image`). * **2026/10/15:** The Wan2.1 training data (42,158 Wan2.1-14B teacher samples with their real-video latents), so `train/wan` can start training right away 🤗 * **2026/10/10:** 8 GB GPUs: a 5 s ComfyUI workflow for 8 GB GPUs, and `--low-vram` in the code repository now makes 5 s videos in under 7 GiB of GPU memory and 15 s videos in 12 GiB 🪶 * **2026/10/08:** 16 GB GPUs: the ComfyUI workflows and `--low-vram` fit in 14 GiB of GPU memory, bit-identical to the larger-GPU runs 🪶 * **2026/10/07:** Ready-to-run ComfyUI workflows (4 and 8 steps, 15 s of video with audio) in `minimax_h3/workflows` 🎛️ * **2026/10/06:** The DMAD weights of Wan2.1 (1.3B, 14B), SDXL and ImageNet-64, and the MiniMax-H3 training data 🤗 * **2026/10/05:** ComfyUI-layout LoRAs of the MiniMax-H3 students, and the training code in the code repository 🏋️ * **2026/10/02:** The 4-step MiniMax-H3 students (`lora_critic`, `full_critic`) released 🚀 Rank-128 LoRAs on the H3 transformer that turn the 50-step teacher into a 4-step generator of 1344x768 video with native stereo audio.

  • marigold-iid-appearance-v1-1↗

    prs-eth

    This is a model card for the `marigold-iid-appearance-v1-1` model for single-image Intrinsic Image Decomposition (IID). The model is fine-tuned from the `stable-diffusion-2` model as described in our papers: - CVPR'2024 paper titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation" - Journal extension titled "Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis" This model type (`appearance`) is trained to perform InteriorVerse decomposition into **Albedo** and two **BRDF material** properties: **roughness** and **metallicity**. Both the input image and the output albedo are in the sRGB color space. For an alternative model type (`lighting`) that performs decomposition into Albedo, Diffuse shading, and Non-diffuse residual, click here.