|
--- |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
- lora |
|
- diffusers |
|
- template:sd-lora |
|
widget: |
|
- text: 'Smile emoji, 4k' |
|
output: |
|
url: images/12.png |
|
- text: 'Love emoji, 4k' |
|
output: |
|
url: images/13.png |
|
- text: 'Cry emoji, 4k' |
|
output: |
|
url: images/14.png |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
instance_prompt: emoji |
|
license: creativeml-openrail-m |
|
--- |
|
# Berenices-Mini-Emoji |
|
|
|
<Gallery /> |
|
Berenices-Mini-Emoji-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 | 27 | |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
for better results use it with the base model /others |
|
|
|
## SETTING-UP |
|
|
|
```py |
|
pipe = StableDiffusionXLPipeline.from_pretrained( |
|
"-------------xxxxxxxxx----------", |
|
torch_dtype=torch.float16, |
|
use_safetensors=True, |
|
) |
|
(or) |
|
----------------------------------------------------------- |
|
pipe = StableDiffusionXLPipeline.from_pretrained( |
|
"stabilityai/stable-diffusion-xl-base-1.0", |
|
torch_dtype=torch.float16, |
|
use_safetensors=True, |
|
) |
|
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) |
|
|
|
pipe.load_lora_weights("prithivMLmods/Berenices-Mini-Emoji-LoRA", weight_name=emojies.safetensors", adapter_name="emoji") |
|
pipe.set_adapters("emoji") |
|
pipe.to("cuda") |
|
``` |
|
|
|
|
|
## Trigger prompts |
|
|
|
Smile emoji, 4k |
|
|
|
|
|
Cry emoji, 4k |
|
|
|
|
|
Love emoji, 4k |
|
|
|
|
|
| Parameter | Value | |
|
|-----------------|---------------------------------------------------------------------------------------| |
|
| Prompt | Smile emoji, 4k| |
|
| Sampler | euler |
|
|
|
## Trigger words |
|
|
|
You should use `emoji` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Berenices-Mini-Emoji-LoRA/tree/main) them in the Files & versions tab. |
|
|
