Model: Anything v4.5
This diffuser is suitable for inference.
Has the following properties that are bundled right out of the box:
- Included: vae
- Half-precision floating point format: fp16
Model Sample Outputs
<p align="center"> <img src="https://huggingface.co/Azher/Anything-v4.5-vae-fp16-diffuser/resolve/main/Image%201.png" alt="Vampire" width="300" height="300" style="display:inline-block;"> <img src="https://huggingface.co/Azher/Anything-v4.5-vae-fp16-diffuser/resolve/main/Image%202.png" alt="Vampire" width="300" height="300" style="display:inline-block;"> <img src="https://huggingface.co/Azher/Anything-v4.5-vae-fp16-diffuser/resolve/main/Image%203.png" alt="Vampire" width="300" height="300" style="display:inline-block;"> <img src="https://huggingface.co/Azher/Anything-v4.5-vae-fp16-diffuser/resolve/main/Image%204.png" alt="Vampire" width="300" height="300" style="display:inline-block;"> </p>
Output Information:
- Prompt:
beautiful, masterpiece, black dress, black hair, red eyes, pale, 1girl, stunning, black collar choker, jeweled earrings
- Negative Prompt:
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, nsfw
- Setup:
Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 11, Size: 512x512
