Dandan: The Working Diary of Female Wukong - Working Cat - Working Meow - Working Dog - Working Wang - Anthropomorphic Animals

1. Model Name:

Dandan: The Working Chronicles of Wukong - Working Cat - Working Meow - Working Dog - Working Pup - Anthropomorphic Animals

2. Creative Inspiration:

Inspired by all "naturally gifted individuals" and "those with inherent talent" who are "laboring the heart, laboring the muscles and bones, starving the skin, emptying the body, causing chaos in their actions," enduring and persevering through challenges in order to "take on major responsibilities."

Using animal anthropomorphic character images to depict various profound stories, with the added ability to integrate product placements into the plot.

3. Model's Training Base: Basic Model_F.1.safetensors

(Full name—Basic Algorithm FLUX,1_dev_fp8; Abbreviated as Basic Algorithm F.1)

4. Sampling Method: FlowMatchEuler

5. Sampling Steps: 10-20 (usually sufficient, not tested beyond 20)

6. Cue Factor: 3-5 (samples used 3.5)

7. Some Positive Cue Phrases:

a cute white female dog, anthropomorphic image, Sitting in front of the computer, typing on the keyboard, CG style,

dandan, Chinese, working,

HDR, UHD, 8K, best quality, masterpiece, Highly detailed, Studio lighting, ultra-fine painting, sharp focus, physically-based rendering,

extreme detail description, Professional, masterpiece, best quality, delicate, beautiful, realistic,

8. Common Negative Cue Phrases:

NSFW, (worst quality:2), (low quality:2), (normal quality:2), low res, normal quality, blurry, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (easynegative:1.2), (unclear eyes:1.331), bad hands, missing fingers, extra digit, (((extra arms and legs))), ng_deepnegative_v1_75t

9. Trigger Words:

The trigger words for the animal anthropomorphic style of Dandan, Female Wukong's Working Chronicles, Working Cat, and Working Dog by Lora:

dandan, Chinese, working,

10. Image Resolution Sizes:

1:1, 3:4, 4:3, 9:16, 16:9,

Custom sizes, not extensively tested yet.

512x768; 768x1024; 768x1024; 864x1536; 600x600; 768x768; 1024x1024; 1536x1536, commonly used natural aspect ratios—show better expressive capability.

11. Other Notes:

(1) This Lora is an original exclusive model participating in the "Inspirational Forest Creative Model Collection Contest" #F.1·Inspiration Innovation#, "#F.1·Infinite Inspiration#" themed activities. Thanks to the LBB platform.

(2) This activity requires model categories to be: Animation Games/Photography/Illustration/E-commerce and Visual Design/Architecture and Spatial Design, with five unique styles of extraordinary creative model works. Additionally, upload at least 3 model example images, with at least 1 image containing generated information.

(3) This Lora is open for use by all other creators, fusion and commercial use allowed.

Fellow creators, including but not limited to, can freely create and use, such as the fusion of traditional and modern styles, the fusion of Chinese style and Western artistic style, the fusion of realistic style and illustrative style, etc., the integration of different artistic categories.

(4) Recommendations for other related parameter settings:

▲ Sampling Method:

In addition to the established FlowMatchEuler pairing, other sampling methods to try include DPM++2M Karras, Eula, Eula A, SDE, with iteration steps: 15-30. Other sampling methods can also be explored such as LCM, with iteration steps ≤15.

▲ Enable High-Resolution Restoration:

For realistic portrayals, recommend using 8x-NMKD-Superscale, 4x-UltraSharp enlargement algorithms; for two-dimensional and 3D large models, R-ESRGAN_4x+ Anime6B, R-ESRGAN_4x+, and other enlargement algorithms can be used.

▲ Test Image Resolution Sizes:

1:1 or 9:16 or 16:9 or 3:4 or 4:3, 512*512, 1024*1024; alternatively, 512*768; or, 768*1024, 600*800, etc. If available, lower than 768, like 512x512, 512x768, 768x512, are recommended for high-resolution restoration.

▲ Suggested Enablement: For drawing character images, enable the After Detailer face retouching plug-in, face_yolov8m, face_yolov8n, face_yolov8n_v2, etc., or multi-unit plug-ins, enable hand parts hand_yolov8n, hand_yolovs, etc.

Welcome to use, create, and share more, friendly exchanges!