It is commonly asked to me that is Stable Diffusion XL (SDXL) DreamBooth better than SDXL LoRA?
Here same prompt comparisons. Not cherry picked. Look prompts and see how well each one following
1st DreamBooth vs 2nd LoRA
3rd DreamBooth vs 3th LoRA
Raw output, ADetailer not used, 1024x1024, 20 steps, DPM++ 2M SDE Karras
Same training dataset
DreamBooth : 24 GB settings, uses around 17 GB
LoRA : 12 GB settings - 32 Rank, uses less than 12 GB
Hopefully full DreamBooth tutorial coming soon to the SECourses YouTube channel.
https://www.youtube.com/SECourses
Experiments (66 full fine tuning), workflow and config files already shared on Patreon.
https://www.patreon.com/posts/very-best-for-of-89213064
Also I am about to publish amazing prompting list for self trained models. Stay tuned and subscribed.
1st Prompt
ohwx man (masterpiece:1.5), (close-up shot:1.8), (extremely intricate:1.2), 8k, highly detailed, A delicate pencil sketch of a ohwx man with flowing hair cascading down his shoulders. The sketch captures the man's serene expression,
no negatives
2nd Prompt
portrait photo of (ohwx man:1.1) wearing an expensive Brown suit, white background, fit
(blue eyes, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), fat, text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
Conclusions: DreamBooth quality is much more superior in terms of realism and also generalization thus styling.
Top comments (0)