1) Always use the tag by darkgem
2) This LoRA was based on the Pony V6 version / Illustrious / SD 1.5
3) Even though the Pony V6 base model is used, some other models may have some inconsistencies in the images, especially in the eyes and hands, if used in Civitai, use some Embedding to get better results. For those who use Comfyui, the best results will be with some Hirefix / DDetailer to improve the image of the character's face.
4) Don't forget to use tags related to the Pony model
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,
5) LoRA weight change in Civitai is at your discretion
6) Add the monochrome, greyscale tag to the negative prompt if you want colored images, as LoRA was composed of black and white images or just one color palette
7) Check first for a model compatible with your chosen image, some models affect Lora in the final result of the image generation for some types such as: furry, human, realistic images, etc. Therefore, the same model may not always be suitable for different types of images.
8) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:
Illustrious
<lora:Darkgem_Style_Lora_Illustrious:1>
Pony
<lora:Darkgem_Style_Lora:0.8>
SD 1.5
<lora:Darkgem_Style_Lora_sd:1>
Note: the number at the end of the Lora name (1) refers to the Lora weight. In image generators, we have a weight slider, but if you want to \"force\" it, use the same number as the image generator slider in the positive prompt, for example:
Illustrious
Civitai slider = 1\n\npositive prompt: <lora:Darkgem_Style_Lora_Illustrious:1>
Pony
Civitai slider = 0.8\n\npositive prompt: <lora:Darkgem_Style_Lora:0.8>
SD 1.5
Civitai slider = 1\n\npositive prompt: <lora:Darkgem_Style_Lora_sd:1>
Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS
Model
Nova Furry XL - Illustrious v3.0
Lora
Darkgem Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)
Advanced
CFG Scale - 3.0 ~ 9.0 (Preferably 5)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably DPM++ 2M Karras)
Steps - 20 ~ 60 (Preferably 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by darkgem, rauru (tears of the kingdom), zonai, the legend of zelda, tears of the kingdom, male focus, solo, 1boy, black penis, furry, on side, black testicles, furry male, lying, jewelry, animal ears, flaccid, large penis, earrings, looking at viewer, white hair, pectorals, piercing, full body, nude, nipples, navel, grey fur, long ears, wide hips, stomach, muscular male, thick thighs, bent legs, long hair, white hair, large thighs, smile
Prompt (Negative)
bad quality, worst quality, worst detail, sketch, censor, human, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, ai-generated
PONY
Model
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
Darkgem Style Lora v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 0.8)
Advanced
CFG Scale - 4.0 ~ 9.0 (Preferably 5)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)
Steps - 20 ~ 50 (Preferably 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by darkgem, detailed, detailed character(s), high quality, high_res, best quality, high quality background, hdr, 4k, 2k, masterpiece, realistic lighting, highly detailed face, white background, bara, 1boy, male focus, muscular male, furry male, muscular, solo, animal ears, furry, tiger, felid, felis, tiger ears, nipples, tiger boy, tongue, large pectorals, tongue out, orange fur, thick eyebrows, upper body, face focus, looking at viewer, nude, close-up, armpits, seductive smile
Prompt (Negative)
zPDXL-neg, 3D, human, monochrome, greyscale
SD 1.5
Model
Indigo Furry Mix - v120_hybrid
Lora
Darkgem Style Lora v1.0 (SD 1.5) - 0.5 ~ 1.0 (Preferably 1)
Advanced
CFG Scale - 5.0 ~ 9.0 (Preferably 7)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably DPM++ 2M Karras)
Steps - 20 ~ 50 (Preferably 30)
Clip Skip - 1/2
VAE - none
Prompt (Positive)
detailed, detailed character(s), high quality, high_res, best quality, high quality background, hdr, 4k, 2k, masterpiece, realistic lighting, highly detailed face, by darkgem, equine, equid, horse, solo, male focus, 1boy, furry male, furry, muscular, muscular male, equine penis, bara, pectorals, from above, erection, selfie, high-angle view, simple background, white background, animal ears, testicles
Prompt (Negative)
aid210, boring_e621_v4, negative_hand-neg, normal quality, low quality, lowres, worst quality, blurry, ugly, bad composition, deformed, mutilation, mutated, bad anatomy, disfigured, wrong anatomy, bad proportions, poorly defined features, cloned face, cross eyed, duplicate error, extra limbs, extra fingers, extra toes, extra tails, deformed hands, deformed feet, mutated hands, fused fingers, floating limbs, missing arms, missing legs, watermark, logo, letters, signature, dialogue, text, username, words, double tail, detached tail, monochrome, greyscale
As this model is based on Pony Diffusion there's not much need to specify anything in the negative prompt, because the Pony model is very flexible, but I always leave the zPDXL-neg tag (https://civitai.com/models/332646/pony-pdxl-negative-embeddings).
General Observations:
If possible, give credit to the author Darkgem while using this LoRA.
Do not sell or commercialize this LoRA, if possible, help the author of the images through your Patreon.
Do not remove metadata from images generated by LoRA.