|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- Green Cartoon |
|
widget: |
|
- text: 'Green Cartoon, a cartoon character is depicted in a vibrant yellow and black outfit. The characters head is adorned with a black headband, adorned with two large round eyes, a white dot in the center, and a black crown on its head. The background is a dark green, adding a pop of color to the scene.' |
|
output: |
|
url: images/GC1.png |
|
- text: 'Green Cartoon, An animated image of a green bird with a yellow beak. The birds head is facing the left side of the image. Its beak is a bright yellow color. Its eyes are black and round. The beak has a yellow stripe on it. Its wings are a vibrant green color. The background is a dark green.' |
|
output: |
|
url: images/GC2.png |
|
- text: 'Green Cartoon, An animated image of a green dachshund dog standing on a black surface. The dogs head is facing the left side of the image, with its mouth slightly open. Its ears are pointed to the left, and its eyes are open. The ears are a dark green, with a black stripe running down the middle of the ears. Its mouth is slightly open, and there are black dots on its stomach. The background is a dark gray wall with a light shining on it.' |
|
output: |
|
url: images/GC3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Green Cartoon |
|
license: creativeml-openrail-m |
|
--- |
|
# Green-Cartoon-Flux-LoRA |
|
|
|
<Gallery /> |
|
|
|
- Hosted Here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC |
|
|
|
**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.** |
|
|
|
## Model description |
|
|
|
**prithivMLmods/Green-Cartoon-Flux-LoRA** |
|
|
|
Image Processing Parameters |
|
|
|
| Parameter | Value | Parameter | Value | |
|
|---------------------------|--------|---------------------------|--------| |
|
| LR Scheduler | constant | Noise Offset | 0.03 | |
|
| Optimizer | AdamW | Multires Noise Discount | 0.1 | |
|
| Network Dim | 64 | Multires Noise Iterations | 10 | |
|
| Network Alpha | 32 | Repeat & Steps | 20 & 2110| |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 11 [ Hi-RES ] |
|
|
|
## Best Dimensions |
|
|
|
- 1024 x 1024 (Default) |
|
|
|
## Setting Up |
|
``` |
|
import torch |
|
from pipelines import DiffusionPipeline |
|
|
|
base_model = "black-forest-labs/FLUX.1-dev" |
|
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16) |
|
|
|
lora_repo = "prithivMLmods/Green-Cartoon-Flux-LoRA" |
|
trigger_word = "Green Cartoon" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Trigger words |
|
|
|
You should use `Green Cartoon` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Green-Cartoon-Flux-LoRA/tree/main) them in the Files & versions tab. |
