SDXL Dev Models
Collection
Are just in initial stage sdxl LoRA
•
17 items
•
Updated
•
5
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
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")
Smile emoji, 4k
Cry emoji, 4k
Love emoji, 4k
Parameter | Value |
---|---|
Prompt | Smile emoji, 4k |
Sampler | euler |
You should use emoji
to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
stabilityai/stable-diffusion-xl-base-1.0