---
language:
- en
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- image-generation
- shuttle

instance_prompt: null
---

# Shuttle Jaguar

Join our [Discord](https://discord.gg/shuttleai) / [Telegram](https://t.me/shuttleai) to get the latest updates, news, and more.

These model variants provide different precision levels and formats optimized for diverse hardware capabilities and use cases
- [bfloat16](https://huggingface.co/shuttleai/shuttle-jaguar/resolve/main/shuttle-jaguar.safetensors)
- [fp8](https://huggingface.co/shuttleai/shuttle-jaguar/resolve/main/fp8/shuttle-jaguar-fp8.safetensors)
- [GGUF](https://huggingface.co/shuttleai/shuttle-jaguar/tree/main/gguf)

![image/png](https://huggingface.co/shuttleai/shuttle-jaguar/resolve/main/demo.png)

Shuttle Jaguar is a text-to-image AI model designed to generate highly aesthetic, cinematic, and realistic images from textual prompts in just four steps, all while being licensed under Apache 2.

## Using the model via API
You can use Shuttle Jaguar via API through ShuttleAI
- [ShuttleAI](https://shuttleai.com/)
- [ShuttleAI Docs](https://docs.shuttleai.com/)

## Using the model with 🧨 Diffusers
Install or upgrade diffusers
```shell
pip install -U diffusers
```
Then you can use `DiffusionPipeline` to run the model
```python
import torch
from diffusers import DiffusionPipeline

# Load the diffusion pipeline from a pretrained model, using bfloat16 for tensor types.
pipe = DiffusionPipeline.from_pretrained(
    "shuttleai/shuttle-jaguar", torch_dtype=torch.bfloat16
).to("cuda")

# Uncomment the following line to save VRAM by offloading the model to CPU if needed.
# pipe.enable_model_cpu_offload()

# Uncomment the lines below to enable torch.compile for potential performance boosts on compatible GPUs.
# Note that this can increase loading times considerably.
# pipe.transformer.to(memory_format=torch.channels_last)
# pipe.transformer = torch.compile(
#     pipe.transformer, mode="max-autotune", fullgraph=True
# )

# Set your prompt for image generation.
prompt = "A cat holding a sign that says hello world"

# Generate the image using the diffusion pipeline.
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=4,
    max_sequence_length=256,
    # Uncomment the line below to use a manual seed for reproducible results.
    # generator=torch.Generator("cpu").manual_seed(0)
).images[0]

# Save the generated image.
image.save("shuttle.png")
```
To learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation

## Using the model with ComfyUI

To run local inference with Shuttle Jaguar using [ComfyUI](https://github.com/comfyanonymous/ComfyUI), you can use this [safetensors file](https://huggingface.co/shuttleai/shuttle-jaguar/blob/main/shuttle-jaguar.safetensors).