Shuttle - Jaguar open-source text-to-image generation model: Produce realistic images with a cinematic feel in four-step inference.

Shuttle Jaguar

Developed by shuttleai

An AI model for text-to-image generation under Apache 2.0 license, capable of producing aesthetically valuable, cinematic-quality realistic images in just four inference steps.

Image Generation EnglishOpen Source License:Apache-2.0 #Four-step rapid generation #Cinematic quality #High-resolution images

Downloads 1,898

Release Time : 1/21/2025

Model Overview

Shuttle Jaguar is an efficient text-to-image generation model that quickly transforms text descriptions into high-quality images, suitable for creative design and content generation.

Model Features

Efficient Inference

Generates high-quality images in just four inference steps, significantly improving generation speed.

Multi-precision Support

Offers bfloat16, fp8, and GGUF quantized versions to adapt to different hardware configurations and usage scenarios.

High-resolution Output

Supports generating high-definition images at 1024x1024 resolution.

Model Capabilities

Text-to-image

Image generation

Use Cases

Creative Design

Artistic Creation

Generates artistic images based on text descriptions.

Produces realistic images with cinematic quality.

Content Generation

Quickly generates visual content for social media or advertising.

Efficiently produces high-quality image content.

🚀 Shuttle Jaguar

Shuttle Jaguar is a text - to - image AI model. It can generate highly aesthetic, cinematic, and realistic images from textual prompts in just four steps. The model is licensed under Apache 2. Join our Discord / Telegram to get the latest updates, news, and more.

✨ Features

These model variants provide different precision levels and formats optimized for diverse hardware capabilities and use cases:

image/png

📦 Installation

Install or upgrade diffusers

pip install -U diffusers

💻 Usage Examples

Using the model via API

You can use Shuttle Jaguar via API through ShuttleAI:

Using the model with 🧨 Diffusers

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 documentation

Using the model with ComfyUI

To run local inference with Shuttle Jaguar using ComfyUI, you can use this safetensors file.

📄 License

This project is licensed under the Apache 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご