Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 1 shared challenge, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
#7 of 23 in Image Editing
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
GPT Image 1
#19 of 23 in Image Editing
Where the votes landed
FLUX.2 [klein] 9B
0%
win rate
Ties
0%
GPT Image 1
0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Outfit Transfer Challenge
Editing“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
AI Judge Analysis
FLUX.2 [klein] 9B
- + Excellent adherence to the clothing details, featuring the correct pea coat and plaid scarf texture.
- + Maintains the original background and identity of the person with high precision.
- + Captures the accessories well, including the watch and jewelry.
- − The person's facial features and vitiligo patterns on the face are slightly modified compared to the source.
- − Includes extra jewelry (beads) not prominently featured in the source clothing image.
GPT Image 1
- + Very clean and professional lighting on the clothing that blends with the subject.
- + Successfully transfers the coat, scarf, and watch from Image 2.
- − Changes the background significantly, losing many of the wooden structure and beach details from Image 1.
- − Alters the subject's face and vitiligo patterns to the point where they no longer match the source person exactly.
- − Crops the image, losing the full-body context requested.
Verdict: FLUX.2 [klein] 9B followed the prompt much more effectively by preserving the original background and the specific details of the wooden structure, while successfully adapting the outfit to the original person's pose. GPT Image 1 generated a high-quality image but failed the source preservation requirement by changing the background and altering the subject's face too much.
Explore each model
OpenAI's previous image generation model that accepts both text and image inputs and produces image outputs