Models tagged "image-to-image"

🤖 Model 🖼️ → 🖼️

arielreplicate/paella_fast_image_variation

Generate variations of an image. Input a single image and receive multiple alternative renderings as output, useful for...

🖼️ → 🖼️ • image-to-image • image-variation • 737 runs

🤖 Model 🖼️ → 🖼️

greeneryscenery/sheeps-control-v3

Generate images from a sketch and a text prompt. Provide a conditioning image (e.g., line art or outline) and a prompt t...

🖼️ → 🖼️ • sketch-to-image • image-to-image • 307 runs

🤖 Model 📝 → 🖼️

cbh123/sdxl-spongebob

Generate SpongeBob-style cartoon images from text prompts. Transform existing images or inpaint masked regions to match...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 115 runs

🤖 Model 📝 → 🖼️

tedkane/sdxl-sketch

Generate sketch-style line art from text prompts or translate existing images into sketch illustrations, with optional i...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 1.5K runs

🤖 Model 📝 → 🖼️

amadad/sdxl-venomyth

Generate comic panels in Joshua Ray Stephens’ style from a text prompt. Optionally transform an input image (img2img) or...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 255 runs

🤖 Model 📝 → 🖼️

galleri5/symbols

Generate curvy minimalist symbols and abstract calligraphic patterns from a text prompt. Accept an optional input image...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 802 runs

🤖 Model 📝 → 🖼️

ghostofpokemon/sdxl-family-guy

Generate Family Guy–style cartoon images from a text prompt, or convert an input image to that style, with optional mask...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 465 runs

🤖 Model 📝 → 🖼️

fofr/sdxl-cross-section

Generate illustrated cross-section and exploded-view images from text prompts. Leverage an SDXL LoRA fine-tune specializ...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 1.2K runs

🤖 Model 🖼️

humanvideointeraction/t2i-adapter-sketch-sdxl

Generate images from a sketch and text prompt. Use SDXL with a ControlNet/T2I-Adapter Scribble to translate line drawing...

🖼️ • sketch-to-image • 289 runs

🤖 Model 📝 → 🖼️

adellcox/sage-v1-fresh

Generates images of a person called sage based on text prompts; optionally takes an input image and mask for image-to-im...

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 32 runs

🤖 Model 📝 → 🖼️

vladasanadev/vlada

Generates images of a person called vlada based on text prompts. The trigger word for this LoRA fine-tune is 'vlada'.

📝 → 🖼️ • text-to-image • lora-person • lora • 46 runs

🤖 Model 📝 → 🖼️

oxanaon/oxana

Generate images of a person called oxana from text prompts or by transforming an input image; outputs images. The trigge...

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 363 runs

🤖 Model 📝 → 🖼️

aideronke/aderonke-lora

Generates images of a person called aderonke based on text prompts. The trigger word for this LoRA fine-tune is 'aderonk...

📝 → 🖼️ • text-to-image • lora-person • lora • 84 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 📝 → 🖼️

richards630620/irathird

Generates images of a person called Irathird based on text prompts. The trigger word for this LoRA fine-tune is 'Irathir...

📝 → 🖼️ • text-to-image • lora-person • lora • 109 runs

🤖 Model 📝 → 🖼️

swk23/livepalpatine

Generate images of Emperor Palpatine based on text prompts. The trigger word for this LoRA fine-tune is 'TOK'.

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 128 runs

🤖 Model 📝 → 🖼️

tracyrepchuk/lora

Generates images of a person called TOK based on text prompts. The trigger word for this LoRA fine-tune is 'TOK'.

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 80 runs

🤖 Model 📝 → 🖼️

aximande/trone_callipyge_white

Generate images of the Trone Callipyge white toilet from text prompts. Optionally provide an input image for image-to-im...

📝 → 🖼️ • text-to-image • image-to-image • toilet • 32 runs

🤖 Model 📝 → 🖼️

jjcall/admm

Generate high-contrast black-and-white street-photography images from a text prompt. Optionally provide an input image (...

📝 → 🖼️ • text-to-image • image-to-image • street-photography • 17 runs

🤖 Model 📝 → 🖼️

philipanheuser/philip

Generates images of a person called Philip based on text prompts. The trigger word for this LoRA fine-tune is 'Philip'.

📝 → 🖼️ • text-to-image • lora-person • lora • 158 runs