fast-inference AI Models

🤖 Model 📝 → 🖼️

black-forest-labs/flux-schnell

Generates images from text prompts using a fast 12 billion parameter rectified flow transformer optimized for speed. Tra...

📝 → 🖼️ • text-to-image • 665.6M runs

🤖 Model 📝 → 🖼️

prunaai/flux.1-dev

Generate images from a text prompt. Emphasizes low latency with selectable speed presets: Lightly Juiced, Juiced, Extra...

📝 → 🖼️ • text-to-image • low-latency • 29.9M runs

🤖 Model 📝 → 🖼️

freepik-company/flux.1-lite-8b-alpha

Generate images from a text prompt. Leverage a lightweight 8B distilled text-to-image transformer that runs about 23% fa...

📝 → 🖼️ • text-to-image • 363 runs

🤖 Model 📝 → 🖼️

prunaai/stable-diffusion-cheetah

Generate one or more images from a text prompt. Use an optimized Stable Diffusion pipeline that runs about 3x faster and...

📝 → 🖼️ • text-to-image • speed-optimized • 190 runs

🤖 Model 📝 → 🖼️

prunaai/hidream-l1-dev

Generates images from text prompts using an optimized version of the HiDream-I1 model. Produces high-quality images acro...

📝 → 🖼️ • text-to-image • 53.4K runs

🤖 Model 📝 → 🖼️

prunaai/sdxl-lightning

Generate images from text prompts with SDXL-Lightning for low-latency, few-step diffusion optimized for A100 inference....

📝 → 🖼️ • text-to-image • sdxl • fast-inference • 669 runs

🤖 Model 📝 → 🎥

wavespeedai/wan-2.1-t2v-720p

Generate 720p videos from text prompts using the Wan 2.1 14B model. Features accelerated inference with multiple speed m...

📝 → 🎥 • text-to-video • 37.0K runs

🤖 Model 📝 → 🖼️

fire/flux

Generate images from a text prompt. Toggle a speed-optimized fp8 Go Fast mode or run in bf16 for higher fidelity. Contro...

📝 → 🖼️ • text-to-image • 115 runs

🤖 Model 📝 → 🎥

wan-video/wan-2.2-t2v-fast

Generates videos from text prompts using a PrunaAI-optimized version of Wan 2.2 A14B for fast and cost-effective video c...

📝 → 🎥 • text-to-video • 283.7K runs

🤖 Model 📝 → 🖼️

arielreplicate/paella_fast_text2image

Generate images from a text prompt quickly. Accepts a prompt and an optional batch size, returning one or more images pe...

📝 → 🖼️ • text-to-image • fast-generation • 804 runs

🤖 Model 📝 → 🖼️

cjwbw/segmind-vegart

Generate images from a text prompt with very few diffusion steps. Use an LCM LoRA acceleration module to sample in 2–8 d...

📝 → 🖼️ • text-to-image • lcm-lora • fast-inference • 767 runs

🤖 Model 📝 → 🖼️

prunaai/wan-2.2-image

Generates cinematic, photorealistic images from text prompts in 3-4 seconds. Produces 2 megapixel images with strong vis...

📝 → 🖼️ • text-to-image • 1.2M runs

🤖 Model 📝 → 🖼️

prunaai/f-lite-juiced

Generate images from a text prompt. Leverage the Freepik/FAL F‑Lite text-to-image model optimized with pruna for roughly...

📝 → 🖼️ • text-to-image • fast-inference • 135 runs