ZMIME
Image model comparison · 2 models · Updated Nov 2, 2026

FLUX.1 [dev] vs Stable Diffusion 3.5 Large

Preferred for text to image: FLUX.1 [dev] · Newest: Stable Diffusion 3.5 Large · Image editing: Neither edits images. Quality scores are blind human-preference votes; specs and prices come from each lab’s listings.

  1. Black Forest Labs

    FLUX.1 [dev]

    Released Aug 1, 2024

    • Text to image
    • Arena969
    • From—
    • Max size—
  2. Stability AI

    Stable Diffusion 3.5 Large

    Released Oct 22, 2024

    • Text to image
    • Arena938
    • From—
    • Max size—
  3. Add a model

    Make it a three-way comparison.

01 — At a glance

Where they differ

Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.

  • Preferred for text to imageFLUX.1 [dev]FLUX.1 [dev] 969 (#78) · Stable Diffusion 3.5 Large 938 (#81) — blind human votes
  • NewestStable Diffusion 3.5 LargeFLUX.1 [dev] Aug 1, 2024 · Stable Diffusion 3.5 Large Oct 22, 2024
  • Widest inputsSame inputsFLUX.1 [dev]: Text prompts · Stable Diffusion 3.5 Large: Text prompts
  • Image editingNeither edits imagesTakes a reference image as input: FLUX.1 [dev] no · Stable Diffusion 3.5 Large no
  • Self-hostingAll open weightsDownloadable weights (FLUX.1 [dev] Non-Commercial License)
  • Most API hostsSame reachFLUX.1 [dev]: 1 · Stable Diffusion 3.5 Large: 1
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

FLUX.1 [dev] vs Stable Diffusion 3.5 Large specifications side by side
SpecificationFLUX.1 [dev]Black Forest LabsStable Diffusion 3.5 LargeStability AI
Quality (blind human votes)
Text to image arenaElo-style score · higher is better969 ±4#78 of 82 · 49,221 votes (best)938 ±4#81 of 82 · 23,396 votes
Output
ProducesImagesImages
Inputs
Text promptsYesYes
Reference images (editing)NoNo
Access
WeightsOpenFLUX.1 [dev] Non-Commercial LicenseOpen
API hosts11
ReleasedAug 1, 2024Oct 22, 2024
03 — Questions

Which should you choose?

Which is better, FLUX.1 [dev] or Stable Diffusion 3.5 Large?

For text to image, voters prefer FLUX.1 [dev] (FLUX.1 [dev] 969 (#78) · Stable Diffusion 3.5 Large 938 (#81)). Arena scores come from blind, side-by-side human votes on the same prompts; when the gap is inside both models’ error margins we call it a tie. Test your own prompts before you commit.

What is the difference between FLUX.1 [dev] and Stable Diffusion 3.5 Large?

FLUX.1 [dev] is an image model from Black Forest Labs (Aug 1, 2024), taking text prompts and producing images. Stable Diffusion 3.5 Large is an image model from Stability AI (Oct 22, 2024), taking text prompts and producing images.

Which is newer?

FLUX.1 [dev] Aug 1, 2024; Stable Diffusion 3.5 Large Oct 22, 2024.

Which can edit an existing image?

Takes a reference image as input: FLUX.1 [dev] no; Stable Diffusion 3.5 Large no.

Can I run any of these on my own hardware?

All open weights. Downloadable weights (FLUX.1 [dev] Non-Commercial License).