AuraFlow v0.3

Piltide genereerimineSaadaval
Community pooltMudeli ID: auraflow-v0-3

fal.ai's fully open-source 6.8B flow-based text-to-image model. Up to 1536x1536 resolution.

Hind
≈ 0,0648 $/kĂ€ivitus
Kuvasuhtarvud
1:1, 16:9, 9:16, 4:3, 3:4
EraldusvÔime
1024×1024, 1536×1536
Sisend → vĂ€ljund
Tekst → Pilt
Arendaja
Community
Uuendatud
23. september 2026
01

Playground

Proovi AuraFlow v0.3

Sisend ja vÀljund

≈ 0,0648 $/kĂ€ivitus
Proovi AuraFlow v0.3

0 / 2000

TĂ€psemad seaded (4)

0 / 1000

Tulemus
Sinu pilt ilmub siia.

See kÀivitus

umbes 0,0648 $ · 6,48 krediiti

KÀivitamisel reserveeritakse 0,1944 $ (19,44 krediiti); arveldatakse tegelik GPU aeg.

Kontode puhul, millel pole ostuajalugu: kĂ€ivitused ĂŒle 2 krediidi vajavad tĂ€iendust.

Oled siin uus?

10 tasuta krediiti (0,10 $), kui registreeritud Google'iga

Kasutatav 24 tundi pÀrast registreerimist, kuni 5 kÀivitust pÀevas ja maksimaalselt 2 krediiti kÀivituse kohta. Muud sisselogimismeetodid algavad ilma krediitideta.

02

Examples

Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
  • Example output 1 from AuraFlow v0.3: a stylized cartoon image, yellow background, a smiling turtle holding a pizza, the turtle is wearing a white and brown cap, large eyes and aOpen full size

    Prompt

    a stylized cartoon image, yellow background, a smiling turtle holding a pizza, the turtle is wearing a white and brown cap, large eyes and a friendly expression, the turtle is standing on its hind legs, the pizza is held in both of its front legs, small clouds and trees on either side of the turtle, the text "Turtle Pizza" is in large brown letters at the top, the text "No More Hungry" at the bottom in brown, the overall style is retro with halftone shading

    Settings

    negative_prompt: ugly, broken

    width
    1024
    height
    1024
  • Example output 2 from AuraFlow v0.3: A stylized cartoon image, pastel pink background, a grinning penguin holding an ice cream cone, the penguin is wearing a colorful striped scOpen full size

    Prompt

    A stylized cartoon image, pastel pink background, a grinning penguin holding an ice cream cone, the penguin is wearing a colorful striped scarf, large eyes and an excited expression, the penguin is waddling on its feet, the ice cream cone is held in one flipper, small icebergs and snowflakes on either side of the penguin, the text "Penguin Scoops" is in large blue letters at the top, the text "Chill Out & Enjoy" at the bottom in blue, the overall style is retro with halftone shading

    Settings

    negative_prompt: ugly, broken

    width
    1024
    height
    1024
  • Example output 3 from AuraFlow v0.3: a close-up portrait photo of a cute cat sitting on a purple armchairOpen full size

    Prompt

    a close-up portrait photo of a cute cat sitting on a purple armchair

    Settings

    negative_prompt: ugly, broken

    width
    1024
    height
    1024
03

Teave: AuraFlow v0.3

LĂŒhidaltSeisuga 23. september 2026

AuraFlow v0.3 on mudel, mille on vĂ€lja töötanud Community kategoorias Piltide genereerimine. Railwail'is maksab AuraFlow v0.3 ≈ 0,0648 $ kĂ€ivituse kohta. Toetatud kuvasuhtarvud: 1:1, 16:9, 9:16, 4:3 ja 3:4.

Taust

Teave fal.ai (AuraFlow) kohta

Asutatud 2021 · New York, USA

AuraFlow is an open-source flow-matching text-to-image model developed primarily by Simo Ryu (the creator of LoRA fine-tuning) in collaboration with fal.ai (a generative-AI inference platform based in New York, founded in 2021 by Burkay Gur, Gorkem Yurtseven and Batuhan Taskaya). After Stability AI announced restrictive licensing changes to Stable Diffusion 3 in mid-2024, Simo Ryu started AuraFlow as a fully open, transparently licensed alternative. fal.ai sponsored the compute. AuraFlow v0.1 launched in July 2024, with v0.2 and v0.3 (August-September 2024) bringing meaningful quality improvements. The project's stated goal is to give the open community a state-of-the-art flow-matching base that is fully Apache 2.0 licensed and can be freely used and fine-tuned for any purpose.

KĂŒlasta fal.ai (AuraFlow)

Arhitektuur

Rectified-flow Diffusion Transformer (DiT) — open-source

AuraFlow v0.3 is the third public checkpoint in the open-source AuraFlow project led by Simo Ryu and sponsored by fal.ai. The architecture is a Diffusion Transformer (DiT) of 6.8B parameters trained with the rectified-flow / flow-matching objective from the SD3 paper (Esser et al. 2024) and the FLUX.1 family. AuraFlow uses a single T5-XXL text encoder (rather than the dual-encoder design of SDXL or the triple-encoder design of SD 3.5) and operates in the latent space of a learned 16x VAE. AuraFlow was the first fully open-source large-scale flow-matching text-to-image model after the closed-source SD3 release; the v0.3 checkpoint introduced substantial quality improvements over v0.2 thanks to additional pretraining tokens, refined data curation and an updated noise schedule. The model and weights are released under the permissive Apache 2.0 license, including commercial redistribution and derivative works.

Parameetrid
6.8B parameters
Kontekst
256 tokenit

VÔimalused

  • Fully Apache 2.0 — commercial use, redistribution and derivatives permitted
  • 6.8B-parameter rectified-flow DiT — one of the largest open models
  • T5-XXL text encoder for strong long-prompt adherence
  • 1024x1024 native resolution
  • Self-hostable on consumer GPUs with quantisation
  • Strong fine-tuning base for community LoRAs and brand models
  • Compatible with Diffusers and ComfyUI
  • Best for: open community fine-tuning, research, fully unrestricted commercial use, on-prem services.

Treening ja litsents

Trained on a curated subset of publicly available image-text data. Simo Ryu has documented dataset choices and ablations publicly, prioritising transparent provenance over closed data.

Litsents: Apache 2.0 — fully open, commercial use, redistribution and derivative works all permitted.

Turvalisuse testimine: No formal red-team report. The open weights ship without an integrated safety classifier and downstream operators are expected to add their own moderation.

Teadaolevad piirangud

  • Quality below FLUX 1.1 [pro] and SD 3.5 Large
  • Smaller training compute than commercial peers
  • Hands, text and complex anatomy imperfect
  • Open weights have no built-in safety filter
04

Hinnad

Hinnad USA dollarites. Kasutamine arvestatakse eelmakstud krediitidest.
TĂŒĂŒpiline kĂ€ivitus (≈ 39 s A100 (80GB) peal)0,0648 $ kĂ€ivituse kohta
GPU-aeg (A100 (80GB))0,00168 $ GPU-sekundi kohta
  • Arvestatakse GPU-aeg, mida kĂ€ivitus tegelikult vĂ”tab. KĂ€ivituse alustamisel reserveeritakse sinu saldost 3× tĂŒĂŒpiline hind ja arvutatakse hiljem.
  • 1 krediit = 0,01 $

Kulukalkulaator

Hinna kalkulaator

s

Pakkuja andmetel tĂŒĂŒpiline: umbes 38,6 s

Kokku

6,48 $

648 krediiti

KĂ€ivituse kohta

0,0648 $ · 6,48 krediiti

Arvestatakse tegelik GPU-aeg; see on hinnang.

05

API

Kutsu AuraFlow v0.3 oma Railwail API vÔtmega. Kasuta selles pÀringus seda mudeli ID-d:
curl https://railwail.com/api/v1/images/generations \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auraflow-v0-3",
    "prompt": "A lighthouse on a rocky coast at sunset, photorealistic"
  }'
MÀÀra oma vÔti kui RAILWAIL_API_KEYLoo API-vÔti
06

Spetsifikatsioonid

Mudeli ID
auraflow-v0-3
Arendaja
Community
Sisend
Tekst
VĂ€ljund
Pilt
Kuvasuhtarvud
1:1, 16:9, 9:16, 4:3, 3:4
EraldusvÔime
1024×1024, 1536×1536
Arveldamine
Kasutuse jÀrgi (tokenid vÔi GPU-aeg)
Mudeli suurus
6.8B parameters
Litsents
Apache 2.0 — fully open, commercial use, redistribution and derivative works all permitted.
Kataloogi kirje uuendatud
23. september 2026

Sisendparameetrid

Mudeli sisendiskeemi sisendid ja seaded. API nÀide jaotises API nÀitab, milliseid neist API aktsepteerib.

  • promptnĂ”utav

    What to generate

    TĂŒĂŒp: Tekst
    Vaikimisi: –
    Lubatud vÀÀrtused: kuni 2000 tÀhemÀrki
  • seed

    Optional seed for reproducibility

    TĂŒĂŒp: TĂ€isarv
    Vaikimisi: –
    Lubatud vÀÀrtused: –
  • size
    TĂŒĂŒp: Valik
    Vaikimisi: 1024x1024
    Lubatud vÀÀrtused: 1024x1024 vÔi 1536x1536
  • aspect_ratio
    TĂŒĂŒp: Valik
    Vaikimisi: 1:1
    Lubatud vÀÀrtused: 1:1, 16:9, 9:16, 4:3 vÔi 3:4
  • guidance_scale
    TĂŒĂŒp: Arv
    Vaikimisi: 3.5
    Lubatud vÀÀrtused: 1 kuni 20
  • negative_prompt

    What to avoid

    TĂŒĂŒp: Tekst
    Vaikimisi: –
    Lubatud vÀÀrtused: kuni 1000 tÀhemÀrki
  • num_inference_steps
    TĂŒĂŒp: TĂ€isarv
    Vaikimisi: 25
    Lubatud vÀÀrtused: 1 kuni 100

Sildid

  • auraflow
  • text-to-image
  • open-weights
  • flow-matching
  • pricing-tbd
07

Kasutamise juhtumid

Milleks seda kasutatakse

  • Open community fine-tuning
  • Fully unrestricted commercial deployments
  • Research and academic experiments
  • Custom brand-style LoRA training
  • On-prem creative pipelines
  • Educational demos of flow-matching
08

Korduma kippuvad kĂŒsimused

Mis on AuraFlow v0.3?

AuraFlow v0.3 on mudel, mille töötas vÀlja Community kategoorias Piltide genereerimine. Railwail'is saad seda kutsuda API vÔtme abil Railwail API kaudu.

Kui palju maksab AuraFlow v0.3 Railwail'is?

Railwail'is maksab AuraFlow v0.3 ≈ 0,0648 $ kĂ€ivituse kohta. Sulle arvestatakse see, mida iga pĂ€ring tegelikult kasutab. Kasutamine makstakse eelnevalt ostetud krediitidest; 1 krediit vĂ”rdub 0,01 $.

Milliseid seadistusi AuraFlow v0.3 toetab?

Vastavalt sisendiskeemile teab AuraFlow v0.3 neid parameetreid: prompt (kuni 2000 tÀhemÀrki), seed, size (1024x1024 vÔi 1536x1536), aspect_ratio (1:1, 16:9, 9:16, 4:3 vÔi 3:4), guidance_scale (1 kuni 20), negative_prompt (kuni 1000 tÀhemÀrki) ja num_inference_steps (1 kuni 100).

Kui kiire on AuraFlow v0.3?

AuraFlow v0.3 kohta ei ole Railwail'is veel piisavalt mÔÔdetud kÀivitusi, et kÀivitusaega vÀita. See sÔltub sisendist, seadistustest ja pakkuja koormusest.

Kas AuraFlow v0.3 on parem kui FLUX 1.1 Pro?

See sĂ”ltub ĂŒlesandest. AuraFlow v0.3 (Community) ja FLUX 1.1 Pro (Black Forest Labs) on mĂ”lemad mudelid kategoorias Piltide genereerimine. VĂ”rdlusleht nĂ€itab nende hindu ja spetsifikatsioone kĂ”rvuti.

VÔrdle AuraFlow v0.3 ja FLUX 1.1 Pro

Kuidas kasutada AuraFlow v0.3 API kaudu?

Loo Railwail API vÔti ja saada oma pÀring mudeli ID-ga auraflow-v0-3. KoodinÀited curl'i, Pythoni ja JavaScripti jaoks on selle lehe API jaotises.

09

VÔrreldavad mudelid

KÔik selles kategoorias
  • SDXL fine-tune by galleri5 for slick flat icons and pop constructivist graphics with thick edges. Trained on Bing generations, it produces clean single-subject icon art that suits app icons, badges and UI glyphs. Raster output, not true vector.

    ≈ 0,0094 $/kĂ€ivitus

    85 % odavam ĂŒhiku kohta

    VÔrdle AuraFlow v0.3 ja Icons (SDXL Flat Pop)
  • InstantIDCommunity

    InstantID makes realistic portraits of a real person from a single reference photo without per-user training. Combines a face encoder with an IdentityNet adapter on SDXL to keep identity and pose while following a text prompt, so it is fast and tuning-free.

    ≈ 0,084 $/kĂ€ivitus

    30 % kallim ĂŒhiku kohta

    VÔrdle AuraFlow v0.3 ja InstantID
  • Sticker MakerCommunity

    fofr's sticker generator that outputs graphics with transparent backgrounds, so the result drops straight into chat apps or print sheets. Runs an SDXL-based pipeline at high speed (default 17 steps) and returns die-cut style art without manual background removal.

    ≈ 0,0055 $/kĂ€ivitus

    92 % odavam ĂŒhiku kohta

    VÔrdle AuraFlow v0.3 ja Sticker Maker

Kasuta AuraFlow v0.3 API kaudu

Üks API vĂ”ti kĂ”igile Railwail mudelitele. Kasutamine arvestatakse eelmakstud krediitidest, 1 krediit = 0,01 $.