Downloads · 30 days
311
60% of all-time downloads
strkyyy/gouache-storybook
gouache-storybook is a text-to-image model from strkyyy. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
This LoRA model transforms your prompts into warm hand-painted gouache illustrations in a charming children's storybook style, featuring visible brushstrokes, soft matte textures, and a cozy muted palette. Apply the t…
Downloads · 30 days
311
60% of all-time downloads
All-time downloads
515
Public
Repo size
107 MB
Likes
1
Public
Click a slice to open those files.
.safetensors93.1 MB · 87%
From the Hugging Face model README
This LoRA model transforms your prompts into warm hand-painted gouache illustrations in a charming children's storybook style, featuring visible brushstrokes, soft matte textures, and a cozy muted palette.
Apply the trigger word 'g0u4ch3' to any prompt for an instant transformation. Ideal strength settings range from 0.6 to 1.0 depending on desired intensity; we recommend starting at 0.85 with EDSampler or LMS and around 25-30 steps.
Use 'g0u4ch3' sparingly to maintain balance between your original prompt and the added illustration style. Experimenting with different samplers can yield unique results.
g0u4ch3 --ar 1:1 --s 750 --q 0.9 little girl in a meadow at sunset, soft lighting, cozy mood
g0u4ch3 medieval castle by the sea, warm golden hour light, grand architecture, romantic composition
g0u4ch3 whimsical robot toy on a vintage desk, soft shadows, playful mood, close-up perspective
g0u4ch3 girl flying with wings over a forest, vibrant colors, dreamy atmosphere, dynamic action shot
g0u4ch3 enchanted garden scene, dappled sunlight through trees, serene and magical ambiance, wide-angle view
g0u4ch3 ethereal abstract swirls of color, soft pastel palette, gentle curves, soothing and mysterious
Activate with g0u4ch3. Recommended strength: 0.9.

diffusersfrom diffusers import AutoPipelineForText2Image
import torch
pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("strkyyy/gouache-storybook")
image = pipe("g0u4ch3, your prompt", num_inference_steps=30).images[0]