뉴스 및 전체 검색

stable-diffusion-inpainting

Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask. The **Stable-Diffusion-Inpainting** was initialized with the weights of the Stable-Diffusion-v-1-2. First 595k steps regular training, then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning to improve classifier-free classifier-free guidance sampling. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. You can use this both with the 🧨Diffusers library and RunwayML GitHub repository ( now deprecated ), Automatic1111 .

sd-vae-ft-mse-flax

These weights are intended to be used with the 🧨 diffusers library. If you are looking for the model to use with the original CompVis Stable Diffusion codebase, come here. We publish two kl-f8 autoencoder versions, finetuned from the original kl-f8 autoencoder on a 1:1 ratio of LAION-Aesthetics and LAION-Humans, an unreleased subset containing only SFW images of humans. The intent was to fine-tune on the Stable Diffusion training set (the autoencoder was originally trained on OpenImages) but also enrich the dataset with images of humans to improve the reconstruction of faces. The first, _ft-EMA_, was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights. It uses the same loss configuration as the original checkpoint (L1 + LPIPS). The second, _ft-MSE_, was resumed from _ft-EMA_ and uses EMA weights and was trained for another 280k steps using a different loss, with more emphasis on MSE reconstruction (MSE + 0.1 * LPIPS). It produces somewhat ``smoother'' outputs. The batch size for both versions was 192 (16 A100s, batch size 12 per GPU). To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replacement for the existing autoencoder.

animagine-xl-4.0-GGUF

GGUF conversions of Animagine XL 4.0 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 `animagine-xl-4.0-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/cagliostrolab/animagine-xl-4.0 — 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_weights

control_v11f1e_sd15_tile

This checkpoint is a conversion of the original checkpoint into `diffusers` format. It can be used in combination with **Stable Diffusion**, such as runwayml/stable-diffusion-v1-5. This checkpoint corresponds to the ControlNet conditioned on **tiled image**. Conceptually, it is similar to a super-resolution model, but its usage is not limited to that. It is also possible to generate details at the same size as the input (conditione) image. @misc{zhang2023adding, title={Adding Conditional Control to Text-to-Image Diffusion Models}, author={Lvmin Zhang and Maneesh Agrawala}, year={2023}, eprint={2302.05543}, archivePrefix={arXiv}, primaryClass={cs.CV} }

stable-diffusion-v2-1-GGUF

Qwen-Image-2.1-Turbo-GGUF

This is a GGUF quantized version of Qwen-Image-2.1-Turbo, the 8-step distilled checkpoint of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-Turbo-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. Every file uses the same per-tensor layout as the matching file in unsloth/Qwen-Image-2.1-GGUF, with an importance matrix collected on Turbo itself at its own 8-step schedule. - Run these with Unsloth Desktop, ComfyUI (ComfyUI-GGUF), stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. Turbo uses the same text encoder and VAE as Qwen-Image-2.1. - VAE: unsloth/Qwen-Image-2.1-FP8 `vae/qwen_image_2.1_vae_bf16.safetensors`. Text encoder: unsloth/Qwen3-VL-8B-Instruct-GGUF `Qwen3-VL-8B-Instruct-UD-Q4_K_XL.gguf`, the Dynamic 2.0 4-bit rung rather than the uniform `Q4_K_M`. - Turbo is meant for **8 steps at CFG 1** with the sampling schedule it ships (`sample_sigmas` in model_index.json). Unsloth Desktop applies it automatically. LPIPS (AlexNet, lower is better) against the bf16 Turbo transformer, same text encoder, VAE, prompts and seeds, 1024x1024, 8 steps, CFG 1, rendered through Unsloth Desktop's diffusers route. Mean with 95% bootstrap CI over 8 prompts x 2 seeds; the held-out column uses 8 further prompts x 2 seeds that were not part of the importance-matrix calibration. Two bf16 runs of the same seeds give 0.000 (run-to-run floor).

stable-audio-3-medium

`Stable Audio 3` is a family of fast latent diffusion models (small, medium, large) for variable length audio generation and editing. Since our models can generate several minutes of audio, variable-length generations are key to avoid the cost of producing full-length generations for short sounds. We also support inpainting, enabling targeted audio editing and the continuation of short recordings. Our latent diffusion models operate on top of a novel semantic-acoustic autoencoder that projects audio into a compact latent space, enabling efficient diffusion-based generation while preserving audio fidelity and encouraging semantic structure in the latent. Finally, we run adversarial post-training to both accelerate inference and improve generation quality, reducing the number of inference steps while improving fidelity and prompt adherence. Stable Audio 3 models are trained on licensed and Creative Commons data to generate music and sounds in less than a 2s on an H200 GPU and less than a few seconds on a MacBook Pro M4. We release the weights of small and medium, that can run on consumer-grade hardware, together with their training and inference pipeline. This model can be used with: 1. the `stable-audio-3` inference and fine-tuning library 2. the `stable-audio-tools` research library We use a publicly available pre-trained T5Gemma model (t5gemma-b-b-ul2) for text conditioning. T5Gemma is redistributed under the Gemma Terms of Use.

sd-1.5-square-quantized

The original source of this model is : runwayml/stable-diffusion-v1-5. This model is just optimized and converted to Intermediate Representation (IR) using OpenVino's Model Optimizer and POT tool to run on Intel's Hardware - CPU, GPU, NPU. We have FP16 and INT8 versions of the model. Please note currently only unet model is quantized to int8. Intended to be used with: - GIMP plugin openvino-ai-plugins-gimp - Blender Addon dream-textures-openvino

tiny-random-stable-diffusion-3