Models tagged "controlnet"

🤖 Model 🖼️ → 🖼️

wolverinn/simple-background

Replace image backgrounds using Stable Diffusion and ControlNet. Input an image to remove its background, generate a new...

🖼️ → 🖼️ • image-editing • background-replacement • stable-diffusion • 4.5K runs

🤖 Model 📝 → 🖼️

cjwbw/kandinsky-2-2-controlnet-depth

Generate images from text or transform an input image using depth-guided ControlNet with Kandinsky 2.2. Takes a text pro...

📝 → 🖼️ • text-to-image • image-to-image • controlnet • 3.8K runs

🤖 Model 📝 → 🖼️

anotherjesse/multi-control

Generate images from a text prompt with multi‑ControlNet conditioning. Accept optional control images to guide structure...

📝 → 🖼️ • text-to-image • image-to-image • controlnet • 60.7K runs

🤖 Model 🖼️

fermatresearch/flux-controlnet-inpaint

Fill masked regions of an image from a text prompt. Accepts an input image, a mask, and an optional ControlNet control i...

🖼️ • image-inpainting • controlnet • lora • 35.9K runs

🤖 Model 📝 → 🖼️

fofr/realvisxl-v3-multi-controlnet-lora

Generate photorealistic images from text prompts, with optional image-to-image and inpainting workflows. Condition outpu...

📝 → 🖼️ • text-to-image • image-inpainting • controlnet • 1.9M runs

🤖 Model 📝 → 🖼️

fofr/latent-consistency-model

Generate images from text prompts or transform input images with ControlNet guidance. Leverage Latent Consistency Models...

📝 → 🖼️ • text-to-image • image-to-image • controlnet • 1.5M runs

🤖 Model 📝 → 🎥

fofr/lcm-animation

Generate short animations from text prompts or a starting image. Animate between a start prompt and an end prompt using...

📝 → 🎥 • text-to-video • image-to-video • controlnet • 30.7K runs

🤖 Model 🖼️ → 🖼️

lightweight-ai/test_sk2ig_f

Generate images from an input image and text prompt, preserving structure via ControlNet edge guidance (HED or Canny). S...

🖼️ → 🖼️ • image-to-image • sketch-to-image • 231 runs

🤖 Model 🖼️ → 🖼️

isomc-stone/test

Generate images from a control image and a text prompt using ControlNet guidance. Accepts an input image (edge map, line...

🖼️ → 🖼️ • image-to-image • sketch-to-image • controlnet • 34 runs

🤖 Model 🖼️ → 🖼️

meepo-pro-player/invoker

Transform an input image according to a text prompt while preserving spatial structure with ControlNet. Accepts an image...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 34.9K runs

🤖 Model 🖼️ → 🖼️

philz1337x/controlnet-deliberate

Edit images from a text prompt while preserving structure using ControlNet Canny guidance. Takes an input image and a pr...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 1.1M runs

🤖 Model 🖼️ → 🖼️

usamaehsan/controlnet-1.1-x-realistic-vision-v2.0

Generate photorealistic images from line art or photos using a text prompt. Use ControlNet 1.1 (lineart) with the Realis...

🖼️ → 🖼️ • image-to-image • sketch-to-image • controlnet • 5.7M runs

🤖 Model 🎥

cjwbw/controlvideo

Transform videos from a source clip and a text prompt into new videos while preserving motion and structure. Condition g...

🎥 • video-to-video • video-editing • controlnet • 2.4K runs

🤖 Model 🎥

lucataco/ltx-video-iclora

Transform videos from a reference video and a text prompt. Preserve motion and scene structure using ICLoRA controls—can...

🎥 • video-to-video • video-editing • 100 runs

🤖 Model 🖼️ → 🖼️

jagilley/controlnet-depth2img

Generate images from an input image and text prompt while preserving scene geometry via depth maps. Use ControlNet depth...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 679.4K runs

🤖 Model 🖼️ → 🖼️

xlabs-ai/flux-dev-controlnet

Generate images from an input image and optional text prompt using ControlNet guidance on Flux.1 Dev. Choose canny, soft...

🖼️ → 🖼️ • image-to-image • controlnet • 257.8K runs

🤖 Model 🖼️ → 🖼️

xlabs-ai/flux-controlnet

Edit images from a text prompt while preserving structure using ControlNet Canny on FLUX.1-dev. Provide an input image a...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 1.8K runs

🤖 Model 📝 → 🖼️

usamaehsan/flux-multicontrolnet

Generate images from a text prompt with multi-ControlNet conditioning. Accept optional control images—canny/edge maps, d...

📝 → 🖼️ • text-to-image • image-to-image • controlnet • 93 runs