Models tagged "text-to-image"

🤖 Model 📝 → 🖼️

qwen/qwen-image

Generate images from text prompts, emphasizing accurate rendering of complex, multilingual text (Chinese, English). Opti...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 814.3K runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-1.1-pro

Generate images from text prompts, with optional composition guidance from a reference image via Flux Redux. Achieve fas...

📝 → 🖼️ • text-to-image • image-to-image • 63.5M runs

🤖 Model 📝 → 🖼️

stability-ai/stable-diffusion-3.5-large-turbo

Generate images from text prompts or transform an input image with prompt-guided edits. Leverage Adversarial Diffusion D...

📝 → 🖼️ • text-to-image • image-to-image • 820.5K runs

🤖 Model 📝 → 🖼️

prunaai/flux.1-dev

Generate images from a text prompt. Optimize for low-latency or consistency with speed modes: Lightly Juiced, Juiced, Ex...

📝 → 🖼️ • text-to-image • 28.1M runs

🤖 Model 📝 → 🖼️

ideogram-ai/ideogram-v2a-turbo

Generate images from text prompts quickly and at low cost. Choose preset styles including General, Realistic, Design, Re...

📝 → 🖼️ • text-to-image • 361.6K runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-1.1-pro-ultra

Generate images from text prompts, with optional reference image guidance to steer composition. Enable ultra mode for up...

📝 → 🖼️ • text-to-image • image-to-image • high-resolution • 18.7M runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-dev-lora

Generate images from text prompts or transform an input image using LoRA fine-tunes. Load LoRA weights from Replicate, H...

📝 → 🖼️ • text-to-image • image-to-image • lora-inference • 4.8M runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-pro

Generate images from text prompts, with optional image conditioning to guide composition. Accepts a text prompt and an o...

📝 → 🖼️ • text-to-image • image-to-image • 13.5M runs

🤖 Model 📝 → 🖼️

ideogram-ai/ideogram-v3-balanced

Generate images from text prompts while balancing speed, quality, and cost. Accept optional image and mask inputs to inp...

📝 → 🖼️ • text-to-image • image-inpainting • 305.1K runs

🤖 Model 📝 → 🖼️

prunaai/wan-2.2-image

Generate images from text prompts in ~3–4 seconds at 1–2 megapixels. Control aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 21...

📝 → 🖼️ • text-to-image • 685.9K runs

🤖 Model 📝 → 🖼️

luma/photon-flash

Generate images from a text prompt at high speed. Guide outputs with optional image, style, and character reference imag...

📝 → 🖼️ • text-to-image • image-to-image • image-consistent-character-generation • 180.6K runs

🤖 Model 📝 → 🖼️

prunaai/hidream-l1-fast

Generate images from a text prompt with low-latency, speed-optimized inference. Control the quality–speed tradeoff via p...

📝 → 🖼️ • text-to-image • 5.0M runs

🤖 Model 📝 → 🖼️

stability-ai/stable-diffusion-3.5-medium

Generate images from text prompts or transform an input image with prompt-guided edits. Leverage Stability AI’s SD 3.5 M...

📝 → 🖼️ • text-to-image • image-to-image • text-rendering • 83.7K runs

🤖 Model 📝 → 🖼️

nvidia/sana-sprint-1.6b

Generate images from a text prompt with 1–4 diffusion steps at very low latency. Accepts a prompt plus optional width/he...

📝 → 🖼️ • text-to-image • 802.9K runs

🤖 Model 📝 → 🖼️

bria/image-3.2

Generate images from a text prompt. Train entirely on licensed data for IP-safe commercial use, using a lightweight 4B-p...

📝 → 🖼️ • text-to-image • licensed-data • text-rendering • 103.8K runs

🤖 Model 📝 → 🖼️

luma/photon

Generate images from text prompts. Optionally guide outputs with image, style, and character reference images using adju...

📝 → 🖼️ • text-to-image • image-style-transfer • image-consistent-character-generation • 3.0M runs

🤖 Model 📝 → 🖼️

google/imagen-3-fast

Generate images from text prompts with low latency and lower cost. Prioritize speed over maximum fidelity while retainin...

📝 → 🖼️ • text-to-image • 522.5K runs

🤖 Model 📝 → 🖼️

stability-ai/sdxl

Generate images from text prompts. Transform existing images toward a prompt (image-to-image) and inpaint masked regions...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 82.5M runs

🤖 Model 📝 → 🖼️

prunaai/hidream-l1-dev

Generate images from a text prompt. Choose speed/quality trade-offs with presets Unsqueezed (highest quality), Lightly J...

📝 → 🖼️ • text-to-image • speed-optimized • 43.9K runs

🤖 Model 📝 → 🖼️

ai-forever/kandinsky-2.2

Generate images from text prompts in multiple languages. Accepts a text prompt (with optional negative prompt) and retur...

📝 → 🖼️ • text-to-image • multilingual • controlnet • 10.0M runs