뉴스 및 전체 검색

MOSS-Image-Base-GGUF

This is a GGUF quantized version of MOSS-Image-Base by OpenMOSS, the 5.1B text-to-image transformer. unsloth/MOSS-Image-Base-GGUF uses Unsloth Dynamic 2.0 methodology: the `UD-` files are mixed precision, with each layer's type chosen from a measured sensitivity scan and an importance matrix collected while generating images. - Runs in Unsloth Studio and in stable-diffusion.cpp builds that include MOSS-Image (master-975 or newer), on CPU, Mac and GPU. - Only the transformer is in these files. The VAE and tokenizer are unchanged; take them from unsloth/MOSS-Image-Base-FP8, which carries the upstream diffusers folders byte for byte. The text encoder runs from the stock unsloth/Qwen3.5-9B-GGUF `Qwen3.5-9B-Q8_0.gguf`. **Recommended:** `MOSS-Image-Base-UD-Q4_K_XL.gguf` (3.42 GB) for most machines: LPIPS 0.179 against 0.293 for `Q4_K_M`. For output closer to bf16 use `UD-Q5_K_XL` (0.138) or `UD-Q6_K_XL` (0.102); `Q8_0` (0.081) is the closest. On a CUDA GPU, Unsloth Studio defaults to the INT8-ConvRot file in unsloth/MOSS-Image-Base-FP8 (LPIPS 0.096) instead. Pick **MOSS-Image-Base** in the Images tab and choose a GGUF file from this repo. Unsloth Studio runs MOSS-Image GGUFs with its bundled stable-diffusion.cpp engine and downloads the VAE, tokenizer and Qwen3.5-9B text encoder for you. Defaults: 1024x1024, 50 steps, CFG 3, shift 5.

Qwen-Image-2.1-Turbo-Uncensored-GGUF

Qwen-Image's text encoder, Qwen3-VL-8B-Instruct, with its refusal direction projected out: a drop-in --llm for stable-diffusion.cpp next to our Turbo denoiser GGUFs . Below, exactly which part is uncensored and what that does to the pictures. The measurements are public. As a chat model, the encoder's refusals fall from 88.9% to 1.2% in English and from 38% to 0% in Russian on held-out prompts. MMLU is unchanged: 77.35% before and after. On images it changes nothing we could measure. The stock Qwen-Image pipeline has no filter and already draws all 9 sensitive categories we tested, and with this encoder not one of 45 prompts changed outcome. See where exactly this is uncensored . Generate images locally in Atomic Chat . It runs stable-diffusion.cpp, the engine these files were built and checked with. Qwen-Image 2.1 makes a picture with three parts. Only one of them is changed here.

Qwen-Image-2512-GGUF

This is a GGUF quantized version of Qwen-Image-2512. unsloth/Qwen-Image-2512-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - To use the model, read our guides for ComfyUI or stable-diffusion.cpp. - Uses tooling from ComfyUI-GGUF by city96. 💜 Qwen Chat &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Tech Report &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp

animatediff-motion-adapter-v1-5-3

AnimateDiff is a method that allows you to create videos using pre-existing Stable Diffusion Text to Image models. It achieves this by inserting motion module layers into a frozen text to image model and training it on video clips to extract a motion prior. These motion modules are applied after the ResNet and Attention blocks in the Stable Diffusion UNet. Their purpose is to introduce coherent motion across image frames. To support these modules we introduce the concepts of a MotionAdapter and UNetMotionModel. These serve as a convenient way to use these motion modules with existing Stable Diffusion models. The following example demonstrates how you can utilize the motion modules with an existing Stable Diffusion text to image model.

lcm-lora-sdv1-5

Latent Consistency Model (LCM) LoRA was proposed in LCM-LoRA: A universal Stable-Diffusion Acceleration Module by *Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.* It is a distilled consistency adapter for `runwayml/stable-diffusion-v1-5` that allows to reduce the number of inference steps to only between **2 - 8 steps**. LCM-LoRA is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first install the latest version of the Diffusers library as well as `peft`, `accelerate` and `transformers`. audio dataset from the Hugging Face Hub:

lcm-lora-sdxl

Latent Consistency Model (LCM) LoRA was proposed in LCM-LoRA: A universal Stable-Diffusion Acceleration Module by *Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.* It is a distilled consistency adapter for `stable-diffusion-xl-base-1.0` that allows to reduce the number of inference steps to only between **2 - 8 steps**. LCM-LoRA is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first install the latest version of the Diffusers library as well as `peft`, `accelerate` and `transformers`. audio dataset from the Hugging Face Hub:

tiny-random-stable-diffusion-with-safety-checker

marigold-iid-lighting-v1-1

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.

FLUX.1-dev-gguf

The license of the quantized files follows the license of the original model: - FLUX.1-dev: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md Run FLUX using stable-diffusion.cpp with a GPU that has 6GB or even 4GB of VRAM: https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/flux.md

stable-diffusion-3.5-large-turbo-gguf