Titania_MIX Realistic版本Realistic Pony GBVR14.0 (ID: 1267686)

It’s tough to generate while training, so I’d really appreciate it if I could receive some Buzz for onsite training, if you’re willing to help.

I’d love to see cosplay submissions using this checkpoint. Please share images!

While the realism might be influenced by the Lora, I'm aiming to find a balance between accurately reproducing the characters from the base model and maintaining responsiveness to both the Lora and the prompts.

[ Pony model ] Pony_Lora is available. Famous characters don’t need Lora.

Sampling method : Euler a , Clip skip : 2

CFG Scale : 2 , Sampling steps : 20

Use ADetailer

Recommended prompt :

score_9, score_8_up, score_7_up, hyper photorealistic:2.5, realistic skin texture, detailed face, detailed eyes, detailed outfit, detailed background, photo\(medium\), sharp focus, BREAK,

Negative prompt:

2D, 3D, source_anime, source_cartoon, source_pony, source_furry, monochrome, bad fingers, bad hands, missing fingers, 5fingers, intersected fingers, disarticulated fingers, ugly fingers, extra fingers, extra arms, extra hands, extra legs, signature, username, motion,

[ Illustrious model ] Illustrious_Lora is available. Famous characters don’t need Lora.

Sampling method : Euler a , Clip skip : 2

CFG Scale : 7 , Sampling steps :30

Use ADetailer. [Inpainting is not required for V40 or later.]

Recommended prompt :

hyper photorealistic, photo\(medium\), masterpiece, best quality, HDR, 4k resolution, intricate details, realistic skin texture, detailed face, detailed eyes, detailed outfit, dramatic lighting, detailed background, high contrast, sharp focus, BREAK,

*It seems that by inputting values like "hyper photorealistic:3," you can generate an image of a cat.

I trained "cat" in the negative, but just to be safe, it might be a good idea to include "cat" in the negative prompt.

Negative prompt:

unrealistic, cat, 2D, 3D, anime, anime face, anime style, cartoon:2.5, painting, flat colors, manga, blurry, lowres, bad quality, low quality, worst quality, jpeg artifacts, text, error, fewer details, extra details, missing details, watermark, unfinished, displeasing composition, outdated style, early generation artifacts, chromatic aberration, signature, extra digits, artistic errors, username, scan artifacts, abstract elements, grainy, overexposed, underexposed, color bleed, overly smooth, plasticky, doll like, wrinkles, frown, scowl, wrinkles, motion,

[ SD1.5 model ] SD1.5_Lora is available.

CFG Scale : 2

Sampling steps : 8

Sampling method : Euler a

Clip skip : 2

描述:

Cute face.

More realistic.

训练词语: