Lumenfall Arena

Leaderboards

All leaderboards
Text-to-Image
Vote All Results
Image Editing
Vote All Results
Text-to-Video
Vote All Results
Image Upscaling
Vote All Results
Image-to-Video
Vote All Results
Text-to-Vector
Vote All Results
Head to head
Esc

Models · slot A

↑↓ to navigate ↵ to pick
Arena / Models / Black Forest Labs

Black Forest Labs

Model evolution · 2024 – 2026
Models
15
Challenges
27
Takes
797
Evolution oldest → newest · 15 versions

How Black Forest Labs models have evolved

One model per node, oldest to newest, each with a sample of its work. These models do different jobs, like image, video, and upscaling, so the chip on each node names its mode. Compare versions within the same mode.

  1. 2024
    FLUX.1 [dev]
    Text-to-Image
    Aug 2024
  2. 2024
    FLUX.1 [schnell]
    Text-to-Image
    Aug 2024
  3. 2024
    FLUX1.1 [pro]
    Text-to-Image
    Oct 2024
  4. 2024
    FLUX.1 [schnell] FP8
    Text-to-Image
    Oct 2024
  5. 2024
    FLUX1.1 [pro] Ultra
    Text-to-Image
    Nov 2024
  6. 2025
    FLUX.1 Kontext [max]
    Text-to-Image
    May 2025
  7. 2025
    FLUX.1 Kontext [pro]
    Text-to-Image
    May 2025
  8. 2025
    FLUX.1 Kontext [dev]
    Text-to-Image
    Jun 2025
  9. 2025
    FLUX.1 Krea [dev]
    Text-to-Image
    Jul 2025
  10. 2025
    FLUX.2 [dev]
    Text-to-Image
    Nov 2025
  11. 2025
    FLUX.2 [flex]
    Text-to-Image
    Nov 2025
  12. 2025
    FLUX.2 [pro]
    Text-to-Image
    Nov 2025
  13. 2025
    FLUX.2 [max]
    Text-to-Image
    Dec 2025
  14. 2026
    FLUX.2 [klein] 4B
    Text-to-Image
    Jan 2026
  15. 2026
    Latest
    FLUX.2 [klein] 9B
    Text-to-Image
    Jan 2026
Smarter every release 22 models

Intelligence over time

How Black Forest Labs's models have grown more capable over time. Each point is one of their models at its release date and arena Elo, oldest to newest.

  • FLUX.1 [dev]
  • FLUX.1 [schnell]
  • FLUX.1 [schnell] FP8
  • FLUX.1 Kontext [dev]
  • FLUX.1 Kontext [max]
  • FLUX.1 Kontext [pro]
  • FLUX.1 Krea [dev]
  • FLUX.2 [dev]
  • FLUX.2 [flex]
  • FLUX.2 [klein] 4B
  • FLUX.2 [klein] 9B
  • FLUX.2 [max]
  • FLUX.2 [pro]
  • FLUX1.1 [pro]
  • FLUX1.1 [pro] Ultra
Head to head

Every challenge, side by side

Each model's take on every challenge in this mode. Modes use different challenges and prompts, so pick one mode at a time; each view stands on its own.

Text-to-Image 17 Image Editing 10
Challenge 10 challenges ↓ · 9 models →
FLUX.1 Kontext [max]
May 2025
FLUX.1 Kontext [pro]
May 2025
FLUX.1 Kontext [dev]
Jun 2025
FLUX.2 [dev]
Nov 2025
FLUX.2 [flex]
Nov 2025
FLUX.2 [pro]
Nov 2025
FLUX.2 [max]
Dec 2025
FLUX.2 [klein] 4B
Jan 2026
FLUX.2 [klein] 9B
Jan 2026
Image Editing

Golden Hour Stroll

9/9 · 27 takes
Image Editing

Golden Hour Stroll

A motion-injection edit test. The model adds wind-driven movement (blowing hair, flying leaves) to a still photo while leaving the rest of the scene intact. The difficulty is making motion look physically plausible without distorting the subject or background.

Edit instruction
“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
Judged on
  • Motion Realism
  • Hair & Cloth Dynamics
  • Edit Localization
  • Photorealism
View full challenge
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Image Editing

Studio Ghibli Anime Style

9/9 · 27 takes
Image Editing

Studio Ghibli Anime Style

A style-transfer test. The model must convert a photo into a convincing hand-painted anime look while preserving the original composition and subject, so the result reads as a genuine illustration rather than a filter laid over the photo.

Edit instruction
“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”
Judged on
  • Style Fidelity
  • Composition Retention
  • Color & Lighting
  • Hand-Painted Texture
View full challenge
3
3
3
3
3
3
3
3
3
Image Editing

Over-the-top cartoon caricature

9/9 · 27 takes
Image Editing

Over-the-top cartoon caricature

A stylized edit test. The model has to exaggerate features for a caricature while keeping the subject recognizable, and work in the requested story elements (profession, dogs, hockey). It balances recognizable likeness against deliberate distortion.

Edit instruction
“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”
Judged on
  • Likeness Retention
  • Caricature Exaggeration
  • Prompt Element Coverage
  • Style Consistency
View full challenge
3
3
3
3
3
3
3
3
3
Image Editing

Bald man challenge

9/9 · 27 takes
Image Editing

Bald man challenge

A targeted edit test. Adding a realistic head of hair requires a believable hairline and texture while keeping the face, expression, and lighting unchanged. Common failures are wig-like or pasted-on hair and subtle changes to the underlying face.

Edit instruction
“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
Judged on
  • Natural Hairline
  • Hair Texture
  • Identity Preservation
  • Lighting Consistency
View full challenge
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
3
Image Editing

Pose & Character Mashup

6/9 · 18 takes
Image Editing

Pose & Character Mashup

This prompt is challenging because it forces models to do two hard things at once: accurately transfer complex body poses and joint angles from Image 1 while strictly preserving the exact face, identity, and clothing style from Image 2. Most models struggle with unnatural limb distortions, identity blending, incorrect fabric behavior on the new pose, and mismatched lighting, making it a strong test of advanced spatial reasoning and character consistency.

Edit instruction
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
Judged on
  • Pose Accuracy
  • Character Consistency
  • Correct Anatomy
  • Lighting Match
View full challenge
No entry yet
No entry yet
No entry yet
3
3
3
3
3
3
Image Editing

Man and Car in California

6/9 · 18 takes
Image Editing

Man and Car in California

Combines two references (a person and a car) into one believable driving scene. It checks whether the model keeps the man’s identity and the car’s appearance while placing them convincingly on the coastline with matched lighting and perspective.

Edit instruction
“Make a photo of the man driving the car down the California coastline”
Judged on
  • Identity Preservation
  • Scene Compositing
  • Lighting Match
  • Photorealism
View full challenge
No entry yet
No entry yet
No entry yet
3
3
3
3
3
3
Image Editing

Outfit Transfer Challenge

4/9 · 12 takes
Image Editing

Outfit Transfer Challenge

This is extremely practical (think e-commerce, fashion, virtual dressing rooms). It’s visually very obvious when it fails, and success looks impressive. It tests a model’s understanding of clothing physics, body shape, and lighting.

Edit instruction
“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.”
Judged on
  • Clothing Accuracy
  • Fit & Fabric Realism
  • Lighting & Shadow Consistency
  • No Side Effects
View full challenge
No entry yet
No entry yet
No entry yet
3
No entry yet
No entry yet
3
3
3
Image Editing

Selective Object Swap

3/9 · 12 takes
Image Editing

Selective Object Swap

Edit instruction
“Swap the positions of the blue and yellow blocks”
View full challenge
No entry yet
No entry yet
No entry yet
No entry yet
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
4
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
4
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
Edited result
Original image
Before After
4
No entry yet
No entry yet