Views
No views yet
A fine-tuned Stable Diffusion model tailored to generate adorable images of a specific pet cat. > Turn your text prompts into fluffy reality.
.jpg) | .jpg) |
| Close-up Portraits | Playful Poses |
diffusers library.pip install diffusers transformers torch1import torch
2from diffusers import StableDiffusionPipeline
3
4model_id = "irkky/my-pet-cat"
5
6# Load the pipeline
7pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
8pipe = pipe.to("cuda")
9
10# Run inference
11# Note: Try using 'xzg cat' or specific tokens if applicable to the training data
12prompt = "A cute xzg cat playing with a ball of yarn, cinematic lighting, 4k"
13image = pipe(prompt).images[0]
14
15# Save your creation
16image.save("my_cat_creation.png")| Feature | Details |
|---|---|
| Model Type | Text-to-Image (Stable Diffusion Fine-tune) |
| Base Model | Stable Diffusion v1.5 (Implied) |
| Language | English |
| License | CreativeML Open RAIL-M |
| Created by | irkky |
unet/: The U-Net architecture (denoising).text_encoder/: The CLIP text encoder.vae/: Variational Autoencoder for decoding latents.tokenizer/: Tokenizer files.scheduler/: Scheduler configuration.xzg.ckpt: Original checkpoint file (2.61 GB).