|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- 3D Portrait |
|
- 3D render |
|
widget: |
|
- text: >- |
|
3D Portrait, An eye-level perspective, a close-up of a young childs face, is |
|
depicted in a multi-colored, monochromatic fashion. The childs eyes are a |
|
piercing blue, and her hair is a vibrant shade of green, with a mix of brown |
|
and orange highlights. Her hair is pulled back in a ponytail, adding a pop |
|
of color to the scene. She is wearing a white turtleneck, and the background |
|
is a pale purple. Her eyebrows are a darker shade of brown, while her lips |
|
are a lighter shade of blue. Her nose is adorned with a tiny red dot. |
|
output: |
|
url: images/3D1.png |
|
- text: >- |
|
3D Portrait, A detailed close-up of a cats face, adorned with a vibrant pink |
|
hue. The cats whiskers, adding a pop of color to the scene. The background |
|
is a deep purple, creating a stark contrast to the cats fur. The cats eyes |
|
are open, as if they are looking to the right. The ears of the cat are |
|
pointed, adding to the overall composition of the image. |
|
output: |
|
url: images/3D2.png |
|
- text: >- |
|
3D Portrait, 3d render of a Hamburger, in the style of light magenta and |
|
light green, macro lens, light purple and light gold, pastelcore, |
|
characterful portraits, zbrush, 3d render, unreal engine |
|
output: |
|
url: images/3D3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: 3D Portrait |
|
license: creativeml-openrail-m |
|
--- |
|
# 3D-Render-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/3D-Render-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 | 27 & 3000| |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 19 [ 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/3D-Render-Flux-LoRA" |
|
trigger_word = "3D Portrait, 3d render" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Data source |
|
|
|
- https://freeflo.ai/ |
|
|
|
## Trigger words |
|
|
|
You should use `3D Portrait, 3d render` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/3D-Render-Flux-LoRA/tree/main) them in the Files & versions tab. |
