DMD2 Speed LoRA [SDXL, Pony, Illustrious] - dmd2_sdxl_4step_lora
ハイライトされた画像
推奨プロンプト
A closeup of a SFW
推奨ネガティブプロンプト
NSFW, naked, nude, watermark, text, simple background
推奨パラメータ
samplers
steps
cfg
other models
ヒント
Recommended LoRA weight: 0.7, but feel free to adjust.
Use the LoRA with any SDXL or similar checkpoint using the recommended settings.
You can merge this LoRA into a checkpoint to include its effects directly.
If results appear washed out or bland, try increasing the CFG scale.
バージョンのハイライト
dmd2_sdxl_4step_lora
dmd2_sdxl_4step_lora_fp32
クリエイタースポンサー
This is the official DMD2 implementation LoRA from the Distribution Matching Distillation for Fast Image Synthesis paper.
Original model at Huggingface tianweiy/DMD2.
Full credit goes to Tianwei Yin.
This is the official DMD2 implementation LoRA from the Improved Distribution Matching Distillation for Fast Image Synthesis paper.
dmd2_sdxl_4step_lora
Original model at Huggingface tianweiy/DMD2.
Recommended Settings
Steps: 8
LoRA weight: 0.7
Sampler: LCM
Scheduler: Normal, Simple
CFG: 1.4 - 1.8
I use similar settings on both a low resolution base image, and the upscaled refinement pass (hires fix).
Usage
Load the LoRA like any other. I recommend a weight of 0.7, but feel free to play around.
You should be able to use it with any SDXL or similar checkpoint. Use the settings above.
You can also merge this into a checkpoint and save that, to include the result of the LoRA into the checkpoint directly. This means you no longer need to load this as a LoRA, and you can still use it with LCM and low steps for good result.
The LoRA itself doesn't add any speed improvement, it just allows you to generate at fewer steps, with better result.
If the results are washed out and bland, try increasing the CFG.
Licence
Creative Commons Attribution Non Commercial 4.0
I am not the creator of the model, just uploading the model here to make it easier to download and reference in creations. Full credit goes to Tianwei Yin.
