Download
1 variant available
770 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
210 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
220 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(7)
Apr 11, 2026
Illustrious
Important notice: While i made the LoRA "more consistent" (not really), you will not get such high eyes fidelity as i did. I utilise a face fixer in ComfyUI to get that level of quality.
I've tried to improve the face anatomy but i failed again... and i give up.
Changes that you might notice or not:
Sharper generation, less blurry face/hair
Slightly better eyes in terms or anatomy
Known issues that i give up fixing:
Her dress dose not come out "sideless" even if you specifically prompt it to.
Her dress might come out as long dress for some reason...
Doing "full body" shots still makes bad eyes.
Show more
1.9K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
3440 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1620 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
License:
Illustrious LicenseThis LoRA was created for a bounty.
How to Use It Effectively
Trigger Word: DriftPixel_EmmaLlama
⚠️ Important: Do not use the trigger word by itself — results will be half-baked. Always combine it with detailed descriptions of pose, expression, outfit, lighting, and mood for the best quality.Recommended Settings
LoRA Weight: 0.9 – 1.2
Sampler: Euler a (recommended) Alternative: DPM++ 2M Karras
Scheduler: Normal or Beta 1.1
Steps: 20 – 40
CFG Scale: 5 – 7
Resolution: 768×1024 (great starting point) I often use 832×1216
Recommended Universal Negative Prompt:
low quality, worst quality, blurry, jpeg artifacts, bad anatomy, bad hands, deformed, distorted, disfigured, extra limbs, missing limbs, malformed limbs, fused fingers, too many fingers, mutated hands, poorly drawn hands, poorly drawn face, long neck, gross proportions, cropped, out of frame, watermark, text, signature, logo, usernameBonus for ComfyUI Users
A full ComfyUI workflow is embedded in the metadata of every sample image I uploaded. Just download any showcase image and drag & drop it into ComfyUI — it will load the complete workflow automatically.This LoRA represents many hours of careful training and testing. If you find it useful, please 👍 like, 💬 leave a comment with your results, and feel free to ⚡ tip. it really helps support future projects!