chinaDollLikeness_v10.safetensors

144 MB · SafeTensor

Memerlukan keahlian

<chinadoll>

Hi, this is author Kbr, several people have requested for this but I was hesitant about it because of certain laws in China related to impersonation and scam, but I still made the LORA anyways. Thank you for waiting. (Please double check the naming of the LORA file when using sample images generation data, Civitai love to rename the LORA file automatically into something different) If you are wondering where are the older versions of my other LORAs, you can find them here on huggingface: My Twitter: My Pixiv: I usually post my works on Twitter and Pixiv. Please consider supporting me at: It takes time and effort to collect training materials, training, testing LORAS, I would appreciate your support! ---------------------------------------------------------------------------------- Introduction 1. This version of TDL does not necessarily mean it is better or worse than v10 and v15, it is a different version that feature a new variety of faces. Recommended settings: - Make sure you are aware on the usage instructions of LORA - VAE: vae-ft-mse-840000-ema-pruned (For realistic models) - Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers) - Steps: 20 to 35 - Clipskip: 1 or 2 - Upscaler : Latent (bicubic antialiased) - CFG Scale : 5 to 9 - LORA weight for txt2img: anywhere between 0.2 to 0.7 are recommended - Denoise strength for img2img: 0.4 to 0.7 - It is also recommended to mix this LORA with my other DollLikeness LORAs for interesting effects ---------------------------------------------------------------------------------- License This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: - You can't use the model to deliberately produce nor share illegal or harmful outputs or content - The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license - You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) (Full license here: ) Additional Add-ons to license/notes - You shall take full responsibility for any creative work that uses this model - Refrain from using this model for malicious intent, harm, defamation, scam or political usages. It may impair and discourage the author from producing more works. Disclaimer Creation of SFW and NSFW images is user's decision, user has complete control over to generate NSFW content whether or not.

SHA256

4D5BA9A5D942D25799CC4C62AB3CF81A403512859A62683BCB44F596C204E65A

ID Model ModelTrends.ai

#462

Sampler

DPM++ SDE Karras

Langkah

45

Guidance

7

Seed

2919878250

Saiz

512x728

Clip skip

2

Sampler

DPM++ SDE Karras

Langkah

28

Guidance

8

Seed

1387974053

Saiz

512x768

Sampler

DPM++ 2M SDE Karras

Langkah

80

Guidance

4

Seed

342617636

Saiz

768x1024

Clip skip

2

Sampler

DPM++ 3M SDE Karras

Langkah

70

Guidance

3

Seed

979129722

Saiz

512x768

Clip skip

2

Sampler

DPM2

Langkah

30

Guidance

5

Seed

1586043918

Saiz

512x768

Clip skip

2

Sampler

DPM++ SDE Karras

Langkah

28

Guidance

8

Seed

3766975706

Saiz

512x768

Sampler

DPM++ 3M SDE Karras

Langkah

70

Guidance

3

Seed

1177217048

Saiz

512x768

Clip skip

2

Sampler

DPM++ SDE Karras

Langkah

28

Guidance

8

Seed

1679624105

Saiz

512x768