Instructions to use 8li/fableframe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 8li/fableframe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("8li/fableframe") prompt = "dreamlikeview" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
fableframe
Model description
FableFrame 3D turns prompts into story-ready scenes in a modern, family-animation style. It favors large, expressive eyes, plush fur and fabrics, toy-scale proportions, and polished PBR shading. Lighting is cinematic—soft bloom, shallow depth of field, tasteful bokeh, and natural rim light—making streets, cafés, beaches, and concert halls pop. It handles humans, animals, and anthropomorphized objects (like cars with faces) consistently, with crisp textures and gentle color grades. Ideal for children’s books, ads, key art, and character branding when you want charm over grit. Not aimed at photorealism; it’s for clean, cozy, high-appeal storytelling visuals.
Trigger words
You should use dreamlikeview to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Training at fal.ai
Training was done using fal.ai/models/fal-ai/flux-lora-fast-training.
- Downloads last month
- 1
Model tree for 8li/fableframe
Base model
black-forest-labs/FLUX.1-dev