Models tagged "image-to-image"

🤖 Model 🖼️ → 🖼️

prunaai/hidream-e1.1

Edit images with text instructions. Provide an input image and a prompt to perform text-guided transformations—style con...

🖼️ → 🖼️ • image-editing • image-to-image • 25.5K runs

🤖 Model 🖼️ → 🖼️

arielreplicate/instruct-pix2pix

Edit images from written instructions. Provide an input image and a natural-language instruction (e.g., add or remove ob...

🖼️ → 🖼️ • image-editing • image-to-image • 42.8K runs

🤖 Model 🖼️ → 🖼️

jagilley/controlnet-hed

Transform an input image based on a text prompt while preserving its structure using HED edge maps. Accepts an image and...

🖼️ → 🖼️ • image-to-image • image-editing • image-style-transfer • 583.2K runs

🤖 Model 🖼️ → 🖼️

jagilley/controlnet-normal

Generate images from an input image and text prompt with normal-map guidance. Use ControlNet to condition Stable Diffusi...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 330.7K runs

🤖 Model 📝 → 🖼️

braxiatel/flux-stickers-lora

Generate sticker-style images from text prompts. Optionally convert an input image to a sticker look or inpaint masked r...

📝 → 🖼️ • text-to-image • image-to-image • sticker-style • 841 runs

🤖 Model 📝 → 🖼️

swk23/obiwan-live-three

Generates images of Obi-Wan Kenobi from text prompts. The trigger word for this LoRA fine-tune is 'TOK'.

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 15 runs

🤖 Model 📝 → 🖼️

busybarbell/asher

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

📝 → 🖼️ • text-to-image • lora-person • lora • 396 runs

🤖 Model 📝 → 🖼️

menilub/menilub

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

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 6 runs

🤖 Model 📝 → 🖼️

marlonbarrios/sdxl-lusterbinds

Generate images of “Lusterbinds”—lustrous, surreal, androgynous figures—from text prompts. Invoke the aesthetic with the...

📝 → 🖼️ • text-to-image • image-to-image • nsfw • 313 runs

🤖 Model 📝 → 🖼️

guillaume-jones/sdxl-germain-outlines

Generate outline drawings of people from text prompts. Apply a Germain line-art/outline style via an SDXL LoRA fine-tune...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 13.9K runs

🤖 Model 📝 → 🖼️

swk23/yoda

Generate images of a character called TOK from text prompts. Optionally transform an input image or fill masked regions...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 85 runs

🤖 Model 📝 → 🖼️

yceballost/telefonica-images-backgrounds

Generate images from text prompts. Transform existing images or fill masked regions with prompt-guided edits using image...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 28 runs

🤖 Model 📝 → 🖼️

swk23/cw-obiwan-live

Generates images of Obi-Wan Kenobi based on text prompts. The trigger word for this LoRA fine-tune is 'TOK'.

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 50 runs

🤖 Model 🖼️ → 🖼️

851-labs/background-remover

Remove backgrounds from images. Accepts an image and returns an edited image with a transparent background (rgba) or a r...

🖼️ → 🖼️ • background-removal • image-editing • 9.2M runs

🤖 Model 📝 → 🖼️

paappraiser/wile_e_coyote_background

Generate classic Looney Tunes Road Runner/Wile E. Coyote–style background art from text prompts. Optionally stylize an i...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 105 runs

🤖 Model 📝 → 🖼️

ludocomito/flux-caravaggio

Generate Caravaggio-style paintings from a text prompt or an input image. Apply Baroque chiaroscuro and tenebrism aesthe...

📝 → 🖼️ • text-to-image • image-to-image • caravaggio-style • 149 runs

🤖 Model 📝 → 🖼️

dunaevai135/tst_agt

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

📝 → 🖼️ • text-to-image • lora-person • lora • 266 runs

🤖 Model 📝 → 🖼️

biggpt1/regina

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

📝 → 🖼️ • text-to-image • lora-person • lora • 52 runs

🤖 Model 📝 → 🖼️

awerbizki/alexej777

Generates images of a person called alexej777 based on text prompts. The trigger word for this LoRA fine-tune is 'alexej...

📝 → 🖼️ • text-to-image • lora-person • lora • 87 runs

🤖 Model 📝 → 🖼️

adriencommery/adcom

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

📝 → 🖼️ • text-to-image • lora-person • lora • 16 runs