Dandan is daydreaming: Ink art male lead in traditional Chinese painting | ink art | Tencent Hyun-DiT

0
0
0
0
AnimeAnime StyleBoyStyle Boost
Recently Updated: First Published:
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info
Anime,Anime Style,Boy,LoRA,HunyuanDiT v1.2Image info

Dandan is daydreaming: national style ink big male lead | character cover | realistic portrait | poster illustration

Character enhancement|Style enhancement|National style black and white painting style|Ink splashing rendering enhancement|Tencent Huan Yuan big model DiT_V1.2

Model introduction: ink style, black and white national style, traditional Chinese painting ink splashing.

Creative overview: The creator has recently been very obsessed with traditional Chinese painting style and ink rendering. The more abundant Chinese elements are seen, the more charming they feel.

Model usage instructions: The checkpoint film is based on the Tencent Huan Yuan DiT_v1.2 big model training.

When testing the small Lora model's production images, other second-dimensional big models, three-dimensional big models, realistic human models, have all been tested, and the ink effect is very good.

Prompt word "Prompt" usage precautions: Trigger words are dandan, ink_art

However, the visual effects of scenes with male characters as the main focus have not been fully tested yet.

Other related parameter settings recommendations:

1. Sampling method: Recommended Eula A, iteration steps: 28.

For other sampling methods, DPM++2M Karras, Eula, iteration steps: 20-30, are recommended. For SDE, the range can be 30-60, or try LCM, with iteration steps ≤15, and so on.

2. Turn on high-resolution restoration: For realistic human big models, it is recommended to use 8x-NMKD-Superscale, 4x-UltraSharp enlargement algorithms; for second-dimensional, 3D big models, R-ESRGAN_4x+ Anime6B and R-ESRGAN_4x+, and other enlargement algorithms can be used.

3. Test image resolution dimensions: 1:1 or 9:16 or 16:9 or 3:4 or 4:3, 512*512, 1024*1024; or, 512*768; or, 768*1024, 600*800, etc. Square and portrait images have a more stable quality.

4. It is recommended to turn on: After Detailer face repair plugin, face_yolov8m, face_yolov8n, face_yolov8n_v2, etc.

Welcome all creators to use, provide feedback, and engage in friendly exchanges.

Discussion

Most popular
|
Newest
Send
Coming Soon
Download
(0.00KB)
Version Details
Type
Generation Count
0
Downloads
0
Recommended Parameters
Recommended Checkpoint
None
Recommended weight
0.8
CFG
7
VAE
None

Gallery

Most popular
|
Newest