Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
LamiaX-000006.safetensors
144 MB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<lamia-lami>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
LamiaEnthusiast
on Civitai
Good LoRa for turning your favorite girl into a lamia. Easy to use and quite adaptable to different situations. It can be combined with the other lamia LoRa for a change in results. Weight: 0.4-1.2 Treat it as the legs factor. The lower the weight, the bigger the chance legs will appear. It worked well with any of the base anime and semi-real models it was tested with. The author recommends using it together with . It works best when the size is increased to around 640x832 or higher. Using 512x512 resolution often causes distorted faces. This LoRa reacts well to such prompts as popular tail colors (blue, red, green, white, and purple) and hair colors. It was trained on many characters who had tops, dresses, or kimonos; those were also tagged as prompts.
Creator notes
This is my latest and only published attempt at making lamia lora. Trained on 110 512x512 lamia pictures with manual tagging. The model however seems to best work when height is incrased to around 512x808 or higher. Using 512x512 resolution often causes distorted faces. All of the images were tagged with "lamia", but reoccuring traits like popular tail colors (blue,red,green,white and purple) and hair colors were also tagged. Many characters also had tops, dresses or kimonos and those were also tagged. I also tagged reoccuring characters with tags miia and jasmin-chan but the lora seems not fit for making accurate art of these characters. I also tagged "tongue", but it seems like the lora is not good at those. Out of the models I tested the winner was abyssOrangeMix2_Hard. All of the generations had their negative promt set as "bad-artist". If you want to get this embedding it should be the one downloadable here: I also want to thank for assisting at tagging the pictures used in training. If you want to help improve this lora you can contact me. I also have versions that were trained more epochs but this seemed to make the overall quality worse. This lora was trained on batch size of 2 and 6 epochs (5 steps per image).The other loras I have are 3,9,12 and 15 epoch versions.
Trigger words
lamia
2,228 downloads · 280 likes on Civitai
SHA256
FF8D3C1B9625DD6D62C249CBB52F6284BEE3E110E3F52AFEEB4A2E76663989E2
ModelTrends.ai Model ID
#117
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
1754684227
Size
512x720
Prompt
<lora:LamiaX-000006:1>lamia, short hair,multicolored hair,red tail,blue tail
Negative prompt
bad-artist
Settings
Sampler
DPM++ 2M
Steps
25
Guidance
6
Seed
1741724387
Size
512x768
Clip skip
2
Weight used
1
Prompt
lamia girl, snake body, snake girl, see no human legs, replace human lower half body with serpent body,, masterpiece, best quality, realistic, snake, unparalleled masterpiece, mesmerizing eyes, female, narrow waist, looking at viewer from top, seductive posture, alluring, clean, beautiful face, pure face, pale skin, stylish hair, divine goddess, shiny skin, skin dentation, delicate pattern, intricate detail, dark jungle environment, dim, bright snake body colour, with cloth, ebony style
Negative prompt
lowers, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad feet, (worst quality, low quality:1.3), makeup, mole under eye, mole, logo, watermark, text, bad legs
Settings
Sampler
DPM++ 2M
Steps
34
Guidance
7
Seed
1088504310
Size
768x512
Clip skip
2
Weight used
1
Prompt
lamia, beautiful lightning, sunset, very detailled, best quality, mkd_vnstyle
Settings
Sampler
DPM++ 2M
Steps
23
Guidance
4
Seed
2003859744
Size
512x768
Clip skip
2
Weight used
0.9
Prompt
lamia, snake body, snake girl, see no human legs, replace human lower half body with serpent body,, masterpiece, best quality, realistic, snake, unparalleled masterpiece, mesmerizing eyes, glowing eyes, female, narrow waist, lying down posture, alluring, clean, beautiful face, pure face, pale skin, tied stylish hair, divine goddess, shiny skin, skin dentation, delicate pattern, intricate detail, room environment, romantic environment, (color:,bright colour) snake body, snake tattoo on body, back pose, sitting pose
Negative prompt
lowers, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad feet, (worst quality, low quality:1.3), mole under eye, mole, logo, watermark, text, bad legs
Settings
Sampler
DPM++ 2M
Steps
34
Guidance
7
Seed
1088504309
Size
768x512
Clip skip
2
Weight used
1
Prompt
lamia, beautiful lightning, sunset, very detailled, best quality, mkd_vnstyle
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
2507046014
Size
512x1024
Prompt
<lora:LamiaX-000006:1>lamia, kimono, short hair,red tail
Negative prompt
bad-artist
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
3736382430
Size
512x1024
Prompt
<lora:LamiaX-000006:1>lamia, short hair,multicolored hair,red tail,blue tail
Negative prompt
bad-artist
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
2738215433
Size
512x808
Prompt
<lora:LamiaX-000006:1>lamia,blonde,black tail,dress
Negative prompt
bad-artist
AI Models for Image, Video & Text Generation
lamia lami is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models