Downloads · 30 days
17
10% of all-time downloads
wizard-s-anima
WizWhite/wizard-s-anima
wizard-s-anima is a text-to-image model from WizWhite. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
All-time downloads
174
Public
Repo size
77.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors76.7 MB · 98%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- May 28, 2025
- Updated
- May 28, 2025
- SHA
- b58563fe
Try a prompt
Base models
Model card
From the Hugging Face model README
Wizard's Anima
<Gallery />Model description
<p>A creature LoRA that aims to improve anthropomorphic animals, with better textures and better use of human-like features.</p><p>Recommended settings (feel free to experiment): <br />Trigger: <code>w1z_an1n4</code><br />LoRA Strength: <code>0.8 - 1.0</code><br />Guidance: <code>3.5</code><br />Steps: <code>20 - 30</code></p><p><strong>Prompt tips: </strong><br />• Detailed species, like <code>barn owl</code>, often give better results than generic ones<br />• Use <code>it/its</code> instead of him/his or she/her<br />• Some animals/prompts seem to be more likely of producing a animated/illustration look, try adding a few <code>photography</code> or <code>cinematic</code> prompt-words<br /></p><p><em><span style="color:#868e96">I don't respond to requests or inquiries about NSFW LoRAs. <br />Please keep gallery free from sexually explicit content – I won't restrict the model, since it gives false positives, and remove stuff that are otherwise fine.</span></em></p>Trigger words
You should use w1z_an1m4 to trigger the generation.
Download model
Weights for this model are available in Safetensors format. Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipe.load_lora_weights('WizWhite/wizard-s-anima', weight_name='w1z-an1m4.safetensors')
image = pipeline('w1z_an1m4, a close-up of a pink flamingo as a fashion model with a bold and futuristic aesthetic. The flamingo is wearing oversized, angular, pink sunglasses with reflective lenses. It also wear large, neon-colored geometric earrings in diamond shapes, one in blue and the other in yellow. Its beak is painted a striking blue, and the eyeshadow is vibrant, blending shades of orange and pink. A colorful choker necklace featuring neon tones complements the accessories. The model’s hair is styled in a sleek, high bun, emphasizing the clean and polished look. The background is minimal and softly lit, ensuring the neon colors and bold accessories stand out prominently. The image is styled in a vibrant, high-fashion editorial manner.').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Fal Ai
- live
- Replicate
- live
- Wavespeed
- live
- Created
- May 28, 2025
- Updated
- May 28, 2025