Files changed (1) hide show
  1. README.md +40 -46
README.md CHANGED
@@ -6,92 +6,86 @@ tags:
6
  - template:diffusion-lora
7
  - flux
8
  - nft
 
9
  - art
 
10
  widget:
11
- - text: 'NFT ++, An eye-level view of a glass milk carton with the words "prithivml" written on it in black letters. The carton is filled with a few dark gray clouds, and there is a white barcode on the left side of the carton. The background is a light blue color.'
12
  output:
13
  url: >-
14
- images/4.png
15
- - text: 'NFT++, A quirky cartoon depiction of a glass cube labeled "prithivmods" in bold white letters. The container is filled with tiny, glowing Polaroid photos floating in a transparent blue liquid. Each photo features a different miniature scene, such as sunsets and faces. A barcode wraps around the bottom left corner of the cube. The background is a gradient of pink and orange, evoking nostalgia.'
16
  output:
17
  url: >-
18
- images/5.png
19
- - text: 'NFT++, A detailed cartoon drawing of glass cube labeled "hf.co" in bold white letters. Inside, a shimmering liquid with hues of blue, purple, and silver flows, dotted with tiny glowing particles resembling stars. A barcode is seamlessly integrated into the container’s sleek design on the back. The background is a midnight blue gradient, adding a celestial feel'
20
  output:
21
  url: >-
22
- images/6.png
23
- - text: 'NFT ++, Captured on a light pink background, a cartoon drawing of a glass container with the word "prithiv-hf" written on it in black letters. The container is filled with a clear liquid, and there are brown bandages inside of the container. There is a barcode on the left side of the box, and a white bar code on the right side. The background is a solid pink.'
24
  output:
25
  url: >-
26
- images/1.png
27
- - text: 'NFT ++, a black and white drawing of a black swan in a glass container. The container is shaped like a hexagon, with a black handle on the right side. The swan is swimming in the water, its head facing towards the left side of the container, its beak slightly open. The water in the container is a dark blue, with white splashes on it. Above the swan, the words "prithiv-hf" are written in bold black letters. The background is a light blue, and the text "prithiv-hf" is written in a bold black font.'
28
  output:
29
  url: >-
30
- images/2.png
31
- - text: 'NFT ++, a cartoon drawing of a cats face is seen in a clear glass container. The container is filled with a variety of brown objects, including a barcode and the word "prithiv" written in black letters. The background is a stark white, with a light brown border. The cats head is adorned with a red ribbon, adding a pop of color to the scene. The word "imo" is written on the top right corner of the container.'
32
- output:
33
- url: >-
34
- images/3.png
35
  base_model: black-forest-labs/FLUX.1-dev
36
- instance_prompt: NFT ++
37
  license: creativeml-openrail-m
38
  ---
39
- ![sdsdsdsd.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/7i8IvME-kTC2VsA9HMPP4.png)
 
40
 
41
  <Gallery />
42
 
43
- # Model description for NFT-Plus-InsideOut-Perspective
 
 
44
 
45
- Image Processing Parameters
46
 
47
- | Parameter | Value | Parameter | Value |
48
- |---------------------------|--------|---------------------------|--------|
49
  | LR Scheduler | constant | Noise Offset | 0.03 |
50
- | Optimizer | AdamW | Multires Noise Discount | 0.1 |
51
- | Network Dim | 64 | Multires Noise Iterations | 10 |
52
- | Network Alpha | 32 | Repeat & Steps | 12 & 2100 |
53
- | Epoch | 11 | Save Every N Epochs | 1 |
54
 
55
- Labeling: florence2-en(natural language & English)
56
 
57
- Total Images Used for Training : 12
58
 
59
  ## Best Dimensions & Inference
60
 
61
- | **Dimensions** | **Aspect Ratio** | **Recommendation** |
62
  |-----------------|------------------|---------------------------|
63
- | 1280 x 832 | 3:2 | Best |
64
- | 1024 x 1024 | 1:1 | Default |
65
 
66
  ### Inference Range
67
 
68
  - **Recommended Inference Steps:** 30–35
69
 
70
  ## Setting Up
 
 
 
71
  ```python
72
  import torch
73
- from pipelines import DiffusionPipeline
74
 
 
75
  base_model = "black-forest-labs/FLUX.1-dev"
76
  pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
77
 
78
- lora_repo = "strangerzonehf/NFT-Plus-InsideOut-Perspective"
79
- trigger_word = "NFT ++"
80
  pipe.load_lora_weights(lora_repo)
81
 
 
 
 
82
  device = torch.device("cuda")
83
  pipe.to(device)
84
- ```
85
- ## Trigger words
86
-
87
- You should use `NFT ++` to trigger the image generation.
88
-
89
- ## Data Source
90
-
91
- quaphadoodle
92
-
93
- ## Download model
94
-
95
- Weights for this model are available in Safetensors format.
96
-
97
- [Download](/strangerzonehf/NFT-Plus-InsideOut-Perspective/tree/main) them in the Files & versions tab.
 
6
  - template:diffusion-lora
7
  - flux
8
  - nft
9
+ - pfp
10
  - art
11
+ - cartoon
12
  widget:
13
+ - text: 'YellowGang, A front-facing view of the character from image_0.png wearing a back-turned black snapback cap, a red basketball jersey with "1" and "YellowGang" logo, gold chains, and holding a small basketball, solid blue background.'
14
  output:
15
  url: >-
16
+ https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-default.png
17
+ - text: 'YellowGang, A character from image_0.png wearing a futuristic cyborg motorcycle helmet with a glowing red LED visor, an astronaut suit with the "YellowGang" patch, and a starry cosmic background.'
18
  output:
19
  url: >-
20
+ https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-cyborg.png
21
+ - text: 'YellowGang, The yellow character from image_0.png clean-shaven (bald), wearing a classic black and white zebra bandana, sleek black aviator sunglasses, and a pink Japanese Kimono with the "YellowGang" logo.'
22
  output:
23
  url: >-
24
+ https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-kimono.png
25
+ - text: 'YellowGang, A close-up portrait of the character from image_0.png with large over-ear DJ headphones, angry red eyes, a spiked leather choker collar, and a blue streetwear hoodie with the "YellowGang" logo, dark city background.'
26
  output:
27
  url: >-
28
+ https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-punk.png
29
+ - text: 'YellowGang, A character from image_0.png with neon green spike hair, "X" dead-style eyes, a tattered military uniform, and a zombie-groan mouth expression.'
30
  output:
31
  url: >-
32
+ https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-zombie.png
 
 
 
 
33
  base_model: black-forest-labs/FLUX.1-dev
34
+ instance_prompt: YellowGang
35
  license: creativeml-openrail-m
36
  ---
37
+
38
+ ![yellowgang_banner.png](https://cdn-uploads.huggingface.co/production/uploads/no-id/placeholder-yellowgang-banner.png)
39
 
40
  <Gallery />
41
 
42
+ # Model description for YellowGang-Generator-LoRA
43
+
44
+ This LoRA model is a specialized generator for the "YellowGang" collection, based on the signature yellow-skinned character style with bold cartoon outlines, as seen in `image_0.png`. It is fine-tuned to preserve the character's facial features and proportions while allowing for high-fidelity generation of diverse traits, including various headwear (bandanas, crowns, helmets), eyewear (cyborg, classic, sleepy), outfits (hoodies, jerseys, armor, suits), and neck accessories (chains, chokers, scarfs). The model ensures the "YellowGang" logo is consistently applied to all outfits.
45
 
46
+ Image Processing Parameters (Used for Training)
47
 
48
+ | Parameter | Value | Parameter | Value |
49
+ |---------------------------|----------|---------------------------|--------|
50
  | LR Scheduler | constant | Noise Offset | 0.03 |
51
+ | Optimizer | AdamW | Multires Noise Discount | 0.1 |
52
+ | Network Dim | 128 | Multires Noise Iterations | 10 |
53
+ | Network Alpha | 64 | Repeat & Steps | 25 & 3500 |
54
+ | Epoch | 15 | Save Every N Epochs | 2 |
55
 
56
+ Labeling: florence2-en(natural language & English) with specific trait tagging.
57
 
58
+ Total Images Used for Training : 20 (Base character + variation set)
59
 
60
  ## Best Dimensions & Inference
61
 
62
+ | **Dimensions** | **Aspect Ratio** | **Recommendation** |
63
  |-----------------|------------------|---------------------------|
64
+ | 1024 x 1024 | 1:1 (Square PFP) | Best (Default for PFP) |
65
+ | 1280 x 832 | 3:2 | Recommended |
66
 
67
  ### Inference Range
68
 
69
  - **Recommended Inference Steps:** 30–35
70
 
71
  ## Setting Up
72
+
73
+ To use this LoRA in your Diffusers pipeline, ensure you use the `YellowGang` instance prompt.
74
+
75
  ```python
76
  import torch
77
+ from diffusers import DiffusionPipeline
78
 
79
+ # Base model on which the LoRA was trained
80
  base_model = "black-forest-labs/FLUX.1-dev"
81
  pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
82
 
83
+ # The location of the fine-tuned LoRA
84
+ lora_repo = "your_username/YellowGang-Generator-LoRA"
85
  pipe.load_lora_weights(lora_repo)
86
 
87
+ # Trigger word to activate the specific character identity
88
+ trigger_word = "YellowGang"
89
+
90
  device = torch.device("cuda")
91
  pipe.to(device)