SD 3.5 Large LoRA
Collection
large, medium, turbo lora
•
7 items
•
Updated
•
10
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
prithivMLmods/SD-3.5-Large-Handpainted-Sketchfab-3D-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 & 2K |
Epoch | 12 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 38
import torch
from diffusers import StableDiffusion3Pipeline
pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("prithivMLmods/SD-3.5-Large-Handpainted-Sketchfab-3D-LoRA", weight_name=" SD3.5-Large-Handpainted-Sketchfab.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")
prompt = "Handpainted, sketchfab, 3D, ured from a low-angle perspective on a gray background, a vibrant purple shotgun is seen in mid-flight. The gun has a silver body, a silver handle, and a brown leather handle. The handle is adorned with silver metal studs, adding a touch of color to the scene. The background is a solid gray, creating a stark contrast to the gun."
negative_prompt = "(lowres, low quality, worst quality)"
image = pipe(prompt=prompt,
negative_prompt=negative_prompt
num_inference_steps=24,
guidance_scale=4.0,
width=960, height=1280,
).images[0]
image.save(f"example.jpg")
You should use Handpainted
to trigger the image generation.
You should use sketchfab
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-3.5-large