Ayumu

CHECKPOINT
Original


Updated:

82K

Another Ayu variant that better with LoRA

✏️ PROMPT SUGGESTION

➕ POSITIVE:

🔹 As always, make it simple and just type your desired prompts. (Masterpiece, best quality and so on), it's not necessary.

➖ NEGATIVE:

🔹 (worst quality, low quality:2)

no need to add really really long prompts like you're writing on thesis, or you'll just got bad results

📝 MY FAVOURITE SETTINGS

🔹 Sampler: DPM++ 2M Karras

🔹 Steps: 20 (for saving credits)

🔹 CFG scale: 7

🔹 Clip skip: 1

🔹 VAE: mse-840000

🔹 Hires fix Upscale: 2x-3x

🔹 Upscaler: Latent, 4x-UltraSharp

🔹 Denoise: 0.4-0.45

*you can also use clip skip 2 to create faces (and some minors) variation.

⚙️ RECOMENDED SETTINGS FOR BEST RESULT

🔹 Use hires fix using settings above.

🔹 For face (optional), you can use ADetailer by choosing face model and set inpaint denoising strength to 0.3-0.4.

🔹 For LCM:

➡️ Steps: 8

➡️ CFG Scale: 1

➡️ Hires fix Upscaler: Latent

➡️ Hires fix Steps: 4

➡️ Denoise: 0.4-0.5

Enjoy it~

And thank you for using my model.

(〃 ̄︶ ̄)人( ̄︶ ̄〃)

If you want to support me, just send me a buffet.

Thank you 💖💖

⚠️ Generation NSFW of real person using this model is strictly prohibited! Please use wisely! ⚠️

Version Detail

SD 1.5
Another Ayu variant that better with LoRA (I think)

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.