Task
Image To Image
S
stabilityai/stable-diffusion-xl-refiner-1.0
Image To Image·stabilityai· 147.8K· 2.0K
diffusers
openrail++
Image To Image
arxiv:2307.01952arxiv:2211.01324arxiv:2108.01073arxiv:2112.10752license:openrail++
SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) is used to generate (noisy) latents, which are then further processed with a refinement model specialized for the final denoising steps. Note that the base model can be used as a standalone module.
# pull & run locally
pip install mlforge-sdk && mlforge pull stabilityai/stable-diffusion-xl-refiner-1.0
pip install mlforge-sdk && mlforge pull stabilityai/stable-diffusion-xl-refiner-1.0
Model details
Provider
stabilityai
Framework
diffusers
Size
29 GB
License
openrail++
Downloads
147.8K
Likes
2.0K
Paper
arXiv:2307.01952
Updated
2023-09-25
About stabilityai/stable-diffusion-xl-refiner-1.0
SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) is used to generate (noisy) latents, which are then further processed with a refinement model specialized for the final denoising steps. Note that the base model can be used as a standalone module.
Related Image To Image
Q
Qwen/Qwen-Image-Edit-2509
509.6K 1.2K
🤗 HF
F
black-forest-labs/FLUX.2-klein-4B
465.2K 772
🤗 HF
Q
lightx2v/Qwen-Image-Edit-2511-Lightning
346.9K 475
🤗 HF
F
unsloth/FLUX.2-klein-4B-GGUF
246.1K 170
🤗 HF
Q
unsloth/Qwen-Image-Edit-2511-GGUF
225.5K 525
🤗 HF
F
black-forest-labs/FLUX.2-small-decoder
196.0K 153
🤗 HF