News and site search

stable-diffusion-xl-base-1.0

stable-diffusion-2-1-base

stable-diffusion-xl-base-1.0

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps. Note that the base model can be used as a standalone module. Alternatively, we can use a two-stage pipeline as follows: First, the base model is used to generate latents of the desired output size. In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") to the latents generated in the first step, using the same prompt. This technique is slightly slower than the first one, as it requires more function evaluations. For research purposes, we recommend our `generative-models` Github repository (https://github.com/Stability-AI/generative-models), which implements the most popular diffusion frameworks (both training and inference) and for which new functionalities like distillation will be added over time. Clipdrop provides free SDXL inference.

dreamshaper-xl-v2-turbo-GGUF

GGUF conversions of DreamShaper XL v2 Turbo for **on-device** image generation with stable-diffusion.cpp. Converted with sd.cpp's `-M convert` so the tensors are correctly named and load directly — the community GGUF quants of this model are mis-exported and fail `get sd version from file`. `Q4_K_S` in a file name: stable-diffusion.cpp wrote the file with `--type q4_K`. Its weight tensors are Q4_K and the other tensors stay F16/BF16/F32. `Q4_K_S` is the closest standard GGUF label, so Hugging Face can list the file. This file was named `dreamshaper-xl-v2-turbo-Q4_K.gguf` before 2026-10-21; the contents are unchanged, and links pinned to an earlier commit still work. **Original model:** https://huggingface.co/Lykon/dreamshaper-xl-v2-turbo — created by its respective authors. **License:** `openrail++` (carried over from the original; its use restrictions apply). This is a format conversion (quantization) only; all credit for the model belongs to the original creators.

stable-diffusion-3.5-large-controlnet-depth

tiny-random-stable-diffusion-xl

tiny-random-stable-diffusion

SSD-1B

Try out the model at Segmind SSD-1B for ⚡ fastest inference. You can also try it on 🤗 Spaces The Segmind Stable Diffusion Model (SSD-1B) is a **distilled 50% smaller** version of the Stable Diffusion XL (SDXL), offering a **60% speedup** while maintaining high-quality text-to-image generation capabilities. It has been trained on diverse datasets, including Grit and Midjourney scrape data, to enhance its ability to create a wide range of visual content based on textual prompts. This model employs a knowledge distillation strategy, where it leverages the teachings of several expert models in succession, including SDXL, ZavyChromaXL, and JuggernautXL, to combine their strengths and produce impressive visual outputs.

illustrious-xl-v2.0-GGUF

GGUF conversions of Illustrious XL v2.0 for **on-device** image generation with stable-diffusion.cpp. Converted with sd.cpp's `-M convert` so the tensors are correctly named and load directly — the community GGUF quants of this model are mis-exported and fail `get sd version from file`. `Q4_K_S` in a file name: stable-diffusion.cpp wrote the file with `--type q4_K`. Its weight tensors are Q4_K and the other tensors stay F16/BF16/F32. `Q4_K_S` is the closest standard GGUF label, so Hugging Face can list the file. This file was named `illustrious-xl-v2.0-Q4_K.gguf` before 2026-10-21; the contents are unchanged, and links pinned to an earlier commit still work. **Original model:** https://huggingface.co/OnomaAIResearch/Illustrious-XL-v2.0 — created by its respective authors. **License:** `creativeml-openrail-m` (carried over from the original; its use restrictions apply). This is a format conversion (quantization) only; all credit for the model belongs to the original creators.

imgmodel

This repo contains a few simple image generation models. You can also load any Stable Diffusion 1.5, SDXL, SD3 or Flux model into KoboldCpp. For SD1.5 and SDXL, you only need the basic model (and VAE fix if no baked VAE). For SD3 and Flux you will also need a Clip and T5-XXL model (not included here) You can use `--sdmodel` to load the base model, and check `--help` for other SD settings. They are all also available in the image tab in the launcher