Models tagged "image-editing"

🤖 Model 📝 → 🖼️

google/nano-banana

Generate and edit images from text prompts and optional reference images. Support multi-image fusion to combine multiple...

📝 → 🖼️ • text-to-image • image-editing • image-to-image • 18.1M runs

🤖 Model 📝 → 🖼️

bytedance/seedream-4

Generate and edit images from text prompts and reference images at up to 4K resolution. Support text-to-image and image-...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 2.4M runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-kontext-max

Edit images via natural-language prompts. Provide an input image and an instruction, or omit the image to generate a new...

📝 → 🖼️ • image-editing • text-to-image • image-style-transfer • 6.5M runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-kontext-pro

Edit images with natural-language prompts. Takes a text instruction and an optional input image, and outputs an edited i...

📝 → 🖼️ • image-editing • text-to-image • image-consistent-character-generation • 27.5M runs

🤖 Model 📝 → 🖼️

qwen/qwen-image

Generate images from text prompts and edit existing images with high-fidelity, multilingual text rendering. Accepts a te...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 718.4K runs

🤖 Model 🖼️ → 🖼️

bytedance/seededit-3.0

Edit images from a text prompt, preserving subjects, backgrounds, and fine details while making targeted changes. Provid...

🖼️ → 🖼️ • image-editing • image-object-removal • image-style-transfer • 292.5K runs

🤖 Model 📝 → 🖼️

bytedance/bagel

Generate and edit images from text and answer questions about images. Accepts a text prompt for text-to-image generation...

📝 → 🖼️ • text-to-image • image-editing • image-to-text • 147.9K runs

🤖 Model 🖼️ → 🖼️

qwen/qwen-image-edit

Edit images from a text instruction and an input image, returning an edited image. Perform both appearance edits (add, r...

🖼️ → 🖼️ • image-editing • image-object-removal • image-text-editing • 599.3K runs

🤖 Model 🖼️ → 🖼️

qwen/qwen-image-edit-plus

Edit images from text instructions using one to three reference images, outputting edited image(s). Combine multiple inp...

🖼️ → 🖼️ • image-editing • image-to-image • image-consistent-character-generation • 1.1M runs

🤖 Model 📝 → 🖼️

lucataco/multi-image-qwen-edit

Edit and merge multiple images based on textual prompts using Qwen-Image-Edit. This experimental model supports fast pre...

📝 → 🖼️ • image-editing • multi-image • text-to-image • 1.6K runs

🤖 Model 🖼️ → 🖼️

espressotechie/qwen-imgedit-4bit

Edit images from text instructions. Provide an input image and a prompt to apply global edits and stylistic transformati...

🖼️ → 🖼️ • image-editing • image-to-image • 345 runs

🤖 Model 📝 → 🖼️

shridharathi/nano-banana-aspect-ratio

Transforms input images based on textual prompts, allowing for aspect ratio selection and output format customization. U...

📝 → 🖼️ • image-editing • image-transformation • aspect-ratio • 2 runs

🤖 Model 🖼️ → 🖼️

black-forest-labs/flux-kontext-dev

Edit images using text prompts. Input an image and a natural-language instruction to modify objects and attributes (colo...

🖼️ → 🖼️ • image-editing • image-style-transfer • 2.4M runs

🤖 Model 🖼️

flux-kontext-apps/text-removal

Remove visible text from an image. Accepts a single image as input and outputs an image with detected text regions remov...

🖼️ • image-object-removal • 55.3K runs

🤖 Model 🖼️ → 🖼️

enhance-replicate/flix_qween_2.0.0

Edit images with text instructions by providing an input image and a prompt, then generate a transformed output image. P...

🖼️ → 🖼️ • image-to-image • image-editing • 2.5K runs

🤖 Model 🖼️ → 🖼️

cjwbw/blipdiffusion

Generate new images of a referenced subject from a text prompt. Takes a reference image and prompt as inputs and outputs...

🖼️ → 🖼️ • image-to-image • image-editing • image-consistent-character-generation • 356 runs

🤖 Model 🖼️ → 🖼️

tengfei-wang/hfgi

Edit facial attributes in an input image and output an edited image. Preserve identity, background, appearance, and illu...

🖼️ → 🖼️ • image-editing • face-editing • 22.2K runs

🤖 Model 🖼️ → 🖼️

gwang-kim/diffusionclip

Edit images by applying preset style transfers and semantic transformations to faces and dog faces using diffusion + CLI...

🖼️ → 🖼️ • image-editing • image-style-transfer • 5.3K runs

🤖 Model 📝 → 🖼️

openai/gpt-image-1

Generate images from text prompts and optional reference images. Accept both text and image inputs and output images, en...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 605.1K runs

🤖 Model 🖼️ → 🖼️

lucataco/omnigen2

Edit images from text instructions and optional reference images, returning a single edited image. Provide one required...

🖼️ → 🖼️ • image-editing • image-to-image • in-context-generation • 1.7K runs