Image-to-image AI Models

Models listed

61

Reviewed and live in this category

Worth weighing up

What goes in and out, licence terms, and whether you can host it yourself

How we treat data

Published specs only — we don't estimate numbers a vendor hasn't stated

Image-to-image models are a source-backed task collection in this directory. The current editorial inventory contains 36 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.

Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.

This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.

Image-to-image model list

Scan the table below, then open any model for pricing, limits and the full write-up.

61 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
Deep Research Max Preview
Google
88.91.0M$2.00$12.00
Gemini Deep Research Preview
Google
88.91.0M$2.00$12.00
Nano Banana 2
Google
62.5131.1K$0.50$60.00
Nano Banana 2
Google
55.265.5K$0.50$60.00
Nano Banana 2 Lite
Google
54.965.5K$0.25$30.00
Nano Banana Pro
Google
49.265.5K$2.00$120.00
Nano Banana Pro
Google
48.165.5K$2.00$120.00
Nano Banana
Google
44.332.8K$0.30$30.00
GPT-Image-2
OpenAI
14.40$5.00$30.00
GPT-Image-1.5
OpenAI
13.60
GPT-Image-1
OpenAI
12.40
1038lab/Qwen-Image-Edit-2511-FP8
1038lab
10.0
Alissonerdx/BFS-Best-Face-Swap
Alissonerdx
10.0
autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime
autoweeb
10.0
black-forest-labs/FLUX.1-Kontext-dev
black-forest-labs
10.0
black-forest-labs/FLUX.2-dev
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-4B
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-4b-fp8
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-9B
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-9b-fp8
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-9b-kv-fp8
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-base-4B
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-base-4b-fp8
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-base-9B
black-forest-labs
10.0
black-forest-labs/FLUX.2-klein-base-9b-fp8
black-forest-labs
10.0
black-forest-labs/FLUX.2-small-decoder
black-forest-labs
10.0
city96/FLUX.2-dev-gguf
city96
10.0
diffusers/FLUX.2-dev-bnb-4bit
diffusers
10.0
Disty0/FLUX.2-klein-4B-SDNQ-4bit-dynamic
Disty0
10.0
dx8152/Flux2-Klein-9B-Consistency
dx8152
10.0
dx8152/Qwen-Edit-2509-Multiple-angles
dx8152
10.0
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
fal
10.0
jdopensource/JoyAI-Image-Edit-Diffusers
jdopensource
10.0
lightx2v/Qwen-Image-Edit-2511-Lightning
lightx2v
10.0
lilylilith/AnyPose
lilylilith
10.0
lilylilith/QIE-2511-MP-AnyLight
lilylilith
10.0
lllyasviel/sd-controlnet-canny
lllyasviel
10.0
lllyasviel/sd-controlnet-openpose
lllyasviel
10.0
lrzjason/Anything2Real
lrzjason
10.0
meituan-longcat/LongCat-Image-Edit
meituan-longcat
10.0
meituan-longcat/LongCat-Image-Edit-Turbo
meituan-longcat
10.0
optimum-intel-internal-testing/tiny-random-flux.2-klein
optimum-intel-internal-testing
10.0
prithivMLmods/Qwen-Image-Edit-2511-Hyper-Realistic-Portrait
prithivMLmods
10.0
prithivMLmods/Qwen-Image-Edit-2511-Ultra-Realistic-Portrait
prithivMLmods
10.0
prithivMLmods/Qwen-Image-Edit-2511-Unblur-Upscale
prithivMLmods
10.0
QuantStack/FLUX.1-Kontext-dev-GGUF
QuantStack
10.0
QuantStack/Qwen-Image-Edit-2509-GGUF
QuantStack
10.0
QuantStack/Qwen-Image-Edit-GGUF
QuantStack
10.0
Qwen/Qwen-Image-Edit
Qwen
10.0
Qwen/Qwen-Image-Edit-2509
Qwen
10.0
Qwen/Qwen-Image-Edit-2511
Qwen
10.0
ScottzillaSystems/qwen-image-edit-plus-nsfw-lora
ScottzillaSystems
10.0
Shar514/Flux-Uncensored-V2
Shar514
10.0
stabilityai/stable-diffusion-xl-refiner-1.0
stabilityai
10.0
starsfriday/Qwen-Image-Edit-2511-Upscale2K
starsfriday
10.0
tencent/HunyuanImage-3.0-Instruct
tencent
10.0
timbrooks/instruct-pix2pix
timbrooks
10.0
tonera/FLUX.2-klein-9B-Nunchaku
tonera
10.0
unsloth/FLUX.2-klein-4B-GGUF
unsloth
10.0
unsloth/FLUX.2-klein-9B-GGUF
unsloth
10.0
unsloth/Qwen-Image-Edit-2511-GGUF
unsloth
10.0

61 models · click a column to sort

About the capability score: a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

Image-to-image model questions

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.