image-editing

paper ,  text-to-image ,  bytedance ,  image-editing ,  self-correction ,  nextflow ,  editcanvas ,  prefix-tuning-grpo ,  optional-diffusion-decoder ,  loss-reweighting ,  multiscale-3d-rope ,  visual-auto-regrressive ,  fixed-computation-budget-packing

text-to-image ,  image-to-image ,  open-weights ,  image-editing ,  flux-2 ,  black-forest-lab ,  flux-2-dev

apple ,  dataset ,  image-editing ,  pico-banana-400k ,  image-editing-dataset ,  text-guided-image-editing ,  text-guided-image-editing-dataset

google ,  image-editing ,  gemini-2-5-flahs-image ,  nano-banana ,  character-consistency ,  multi-image-fusion

paper ,  image-editing ,  omnigen ,  unified-image-generation ,  any-to-image ,  subject-driven-generation ,  x2i ,  x2i-dataset

generative ,  multimodal ,  paper ,  meta-ai ,  text-to-image ,  image-editing ,  transfusion

apple ,  multimodal ,  lmm ,  mllm ,  image-editing ,  mgie

text-to-image ,  diffusion ,  rotationdrag ,  image-editing ,  dragdiffusion ,  instructpix2pix ,  freedrag ,  imagic ,  point-to-image