Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0Trigger word
Use animated-style in your prompt to activate the style.
markdown
animated-style a fox standing on a cliff overlooking the ocean, fluffy clouds in a bright blue sky
Files
| File | Notes |
|---|---|
animation-000004.safetensors | Epoch 4 checkpoint (early — more checkpoints coming) |
Usage
Works with any FLUX-capable UI (ComfyUI, Forge, etc.) — place the file in your LoRA folder and load at strength 0.7–1.2.
With 🧨 diffusers:
python
import torchfrom diffusers import FluxPipelinepipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16)pipe.load_lora_weights("yasaone1919/flux-schnell-stylized-animation-lora", weight_name="animation-000004.safetensors")pipe.to("cuda")image = pipe("animated-style a fox standing on a cliff overlooking the ocean",num_inference_steps=4,guidance_scale=0.0,).images[0]image.save("out.png")
Training details
- Base model: FLUX.1-schnell (fp8)
- Trainer: kohya-ss/sd-scripts via fluxgym
- Dataset: 10 stylized animation frames, auto-captioned with Florence-2
- Network dim: 4, LR 8e-4, adafactor, 512px, bf16 mixed precision
- Trained on a single RTX 3070 Ti (8 GB) using 35-block CPU swapping
Model provider
yasaone1919
Model tree
Base
black-forest-labs/FLUX.1-schnell
Adapter
this model
Modalities
Input
Text
Output
Image
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information