DMD2 Speed LoRA [SDXL, Pony, Illustrious]
Updated 8/18/2025
![DMD2 Speed LoRA [SDXL, Pony, Illustrious] preview 1](https://cdn.girlfriendly.ai/model-previews/2025/10/26/file-8vBSRmRXnG5i/0.webp)
![DMD2 Speed LoRA [SDXL, Pony, Illustrious] preview 2](https://cdn.girlfriendly.ai/model-previews/2025/10/26/file-8vBSRmRXnG5i/1.webp)
![DMD2 Speed LoRA [SDXL, Pony, Illustrious] preview 3](https://cdn.girlfriendly.ai/model-previews/2025/10/26/file-8vBSRmRXnG5i/2.webp)
![DMD2 Speed LoRA [SDXL, Pony, Illustrious] preview 4](https://cdn.girlfriendly.ai/model-previews/2025/10/26/file-8vBSRmRXnG5i/3.webp)
![DMD2 Speed LoRA [SDXL, Pony, Illustrious] preview 5](https://cdn.girlfriendly.ai/model-previews/2025/10/26/file-8vBSRmRXnG5i/4.webp)
About this model
This is a LoRA implementation of the Distribution Matching Distillation (DMD2) method for fast image synthesis with SDXL. It enables image generation with fewer steps while maintaining quality, especially when using LCM sampler and a low step count. Recommended settings include 8 steps, LoRA weight of 0.7, and a CFG between 1.4-1.8; it can be merged into a checkpoint for direct usage.
Version: dmd2_sdxl_4step_lora_fp32
DMD2 Speed LoRA [SDXL, Pony, Illustrious] dmd2_sdxl_4step_lora_fp32
Posts with this model
No posts found for this model version. Be the first to create something with it!