IndigoFurryMixXL_EPS3

Indigo Furry Mix XL

Converted from SafeTensor checkpoint to Diffusers format Original: https://civitai.com/models/579632?modelVersionId=1472080

Model Information

• Base Model: Laxhar/noobai-XL-1.0
• Original Format: SafeTensor Checkpoint
• Converted Format: Diffusers
• Model Type: Stable Diffusion XL
• Original Checkpoint: indigoFurryMixXL_noobaiEPS3.safetensors

Usage

Basic Usage

from diffusers import StableDiffusionXLPipeline
import torch

# Load the pipeline
pipeline = StableDiffusionXLPipeline.from_pretrained(
    "your-username/your-repo-name", 
    torch_dtype=torch.float16,
    use_safetensors=True
)
pipeline = pipeline.to("cuda")

# Generate an image
prompt = "a beautiful landscape, masterpiece, best quality"
negative_prompt = 'low quality, blurry, distorted'
image = pipeline(
    prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=25,
    guidance_scale=7.5,
    width=1024, height=1024
).images[0]

image.save("generated_image.png")

Advanced Usage with Custom Settings

# For more control over generation
image = pipeline(
    prompt="your prompt here",
    negative_prompt='low quality, worst quality',
    num_inference_steps=30,
    guidance_scale=8.0,
    width=1024,
    height=1024,
    generator=torch.Generator("cuda").manual_seed(42)
).images[0]

Recommended Settings

For NoobAI Models:

• Positive prompts: Include 'masterpiece, best quality, very aesthetic'

• Negative prompts: Use 'lowres, bad anatomy, bad hands, text, error, missing fingers'

• CFG Scale: 5-7 recommended

• Resolution: 1024x1024 or 832x1216 for portraits

• Steps: 20-30 steps usually sufficient

• Sampler: Euler a, DPM++ 2M, or DPM++ SDE work well

Model Details

This model was automatically converted from a SafeTensor checkpoint to the Diffusers format for easy use with the 🤗 Diffusers library.

Technical Specifications

• Architecture: Stable Diffusion XL
• Parameter Count: ~3.5B
• Precision: Mixed precision (FP16/FP32)
• VRAM Requirements: ~6GB (with FP16)

License

This model is licensed under the CreativeML OpenRAIL-M license. Please ensure you comply with the license terms when using this model.

Disclaimer

This model is converted from a community checkpoint. Please ensure you have the right to use and distribute the original model before using this converted version.