Tensor.Art Green
Create

Mouth pronouncing

LORA
Reprint

Updated:

O Type2-V2
E Type2-V2
U Type2-V2
I Type2-V2
A Type2-V2
O Type1-V2
E Type1-V2
U Type1-V2
I Type1-V2
A type1-V2
O (/o/)
E (/e/)
I (/i/)
U (/ɯ/)
A (/a/)

Reproduces mouths pronouncing Japanese basic vowel, "A" (Ah; /a/) .

Other vowels : "I" (Ee; /i/) , "U" (Woo; /ɯ/) , "E" (Eh; /e/) , "O" (Oh; /o/) are also available.

It also can be applied to a variety of other applications depending on its shape.

Use with open mouth prompt.

Mouth size can be controlled by LoRA weight to some extent.

On my HuggingFace repo, you can download more various other LoRAs. please check it out.

https://huggingface.co/JujoHotaru/lora

Version Detail

SD 1.5
Reproduces mouths pronouncing Japanese basic vowel, "E" (Eh; /e/) . This is "Type 1", and has a slightly different shape than Type 2. Five vowels (and two types) are also available: "A" (あ; Ah; /a/) : Type1 / Type2 "I" (い; Ee; /i/) : Type1 / Type2 "U" (う; Woo; /ɯ/) : Type1 / Type2 "E" (え; Eh; /e/) : Type1 / Type2 "O" (お; Oh; /o/) : Type1 / Type2 It also can be applied to a variety of other applications depending on its shape. Suitable for anime-style models. With most photorealistic models, it won't work well. My checkpoints, such as AngelBreed, ArchAngelBreed, SylphBreed and HotaruBreed series, will reproduce good results. Usage Use with open mouth prompt. Mouth size can be controlled by LoRA weight to some extent. More various other LoRA's and checkpoints are released on my CivitAI models list or HuggingFace repository. Please check it out. CAUTION : Some sample images' prompt is using NegPiP extension for minus weight.

Project Permissions

Model reprinted from : https://civitai.com/models/150339/mouth-pronouncing-a-a

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.