Models tagged "image-to-image"

🤖 Model 📝 → 🖼️

iamprofessorex/retro-scifi-vibes

Generate retro‑futuristic sci‑fi style images from a text prompt. Optionally provide an input image for image-to-image s...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 112 runs

🤖 Model 🖼️ → 🖼️

smoosh-sh/baby-mystic

Generate a baby portrait from two parent photos. Provide one image of each parent and optionally choose gender (boy or g...

🖼️ → 🖼️ • image-to-image • baby-generation • face-generation • 3.9M runs

🤖 Model 📝 → 🖼️

andyx1976/realunifshirt

Generate images of military uniform shirts from a text prompt. Optionally condition on an input image or provide a mask...

📝 → 🖼️ • text-to-image • image-to-image • military-uniform • 1.8K runs

🤖 Model 📝 → 🖼️

fofr/sdxl-ghostbusters

Generate Ghostbusters-style images from text prompts. Optionally transform an input image (img2img) or inpaint with a ma...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 927 runs

🤖 Model 📝 → 🖼️

smkrv/panelka-flux

Generate moody Eastern Bloc and post‑Soviet urban scenes from text prompts. Produce images of brutalist concrete panel h...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 55 runs

🤖 Model 📝 → 🖼️

fofr/flux-90s-power-rangers

Generate 1990s Power Rangers–style images from text prompts. Optionally convert an input image or fill masked regions to...

📝 → 🖼️ • text-to-image • image-to-image • power-rangers • 204 runs

🤖 Model 📝 → 🖼️

avastrettongmail/psychelink

Generate images in the “psychelink” style from text prompts, or transform an input image with optional masking for inpai...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 83 runs

🤖 Model 📝 → 🖼️

khaihuyennguyen/northprint

Generate vintage print–style images from text prompts or transform input images into that aesthetic. Optionally inpaint...

📝 → 🖼️ • text-to-image • image-to-image • vintage-print • 36 runs

🤖 Model 📝 → 🖼️

asiryan/kolors

Generate images from text or transform an input image based on a prompt. Accepts a text prompt and an optional source im...

📝 → 🖼️ • text-to-image • image-to-image • 22.6K runs

🤖 Model 📝 → 🖼️

sundai-club/sidequest

Generate images from text prompts, with optional image-to-image translation and masked inpainting. Leverage a fine-tuned...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 7 runs

🤖 Model 📝 → 🖼️

sundai-club/pawse

Generate images from text prompts. Optionally transform an input image (img2img) or fill masked regions for inpainting,...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 9 runs

🤖 Model 📝 → 🖼️

topogoogles/topogoogles4

Generate consistent, style-locked images from text prompts. Optionally transform an input image or fill masked regions f...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 3 runs

🤖 Model 🖼️ → 🖼️

chenxwh/ominicontrol-spatial

Edit images from an input image and text prompt, outputting an image with spatially aligned control. Apply edge-guided g...

🖼️ → 🖼️ • image-to-image • image-inpainting • image-colorization • 108 runs

🤖 Model 🖼️ → 🖼️

tgohblio/instant-id-multicontrolnet

Generate identity-consistent images of a person from a face image and a text prompt. Preserve facial likeness with Insta...

🖼️ → 🖼️ • image-consistent-character-generation • image-to-image • 311.4K 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

🤖 Model 📝 → 🖼️

christianmendoza77/hellophotos

Generate lifestyle photography images in the HelloHello brand style from text prompts. Optionally transform an input ima...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 6 runs

🤖 Model 📝 → 🖼️

andyx1976/bash

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

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 4 runs

🤖 Model 📝 → 🖼️

vespo300/mar24

Generates images of a person called TOKMAR based on text prompts or an input image. The trigger word for this LoRA fine-...

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 9 runs

🤖 Model 📝 → 🖼️

bytedance/seedream-5

Generate and edit images from text prompts and reference images. Apply multi-step reasoning to respect spatial relations...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 23 runs

🤖 Model 📝 → 🖼️

swk23/thrawn

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

📝 → 🖼️ • text-to-image • lora-person • image-to-image • 91 runs