Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
AndroFlux - v11-3600 thumbnail

AndroFlux - V11-3600

by ModelsLab

Changelog from v8 Configuration

  • MAX_NUM_STEPS: 10000 >> 30000

  • CHECKPOINTING_STEPS: 100 >> 200

  • TRAIN_BATCH_SIZE: 2 (unchanged)

  • GRADIENT_ACCUMULATION_STEPS: 1 >> 2

  • RESOLUTION: 1024 >> 512

  • LEARNING_RATE: 1.0 (unchanged)

  • OPTIMIZER: Prodigy (unchanged)

  • VALIDATION_GUIDANCE: 3.5 (unchanged)

  • VALIDATION_GUIDANCE_REAL: 1.0 >> 2.0

  • INSTANCE_PROMPT: Not Set >> "AndroFlux, "

  • TRAINER_EXTRA_ARGS:

    • base_model_precision: fp8-quanto (unchanged)

    • lora_rank: 8 >> 16

    • max_grad_norm: 0.01 >> 1.0

    • gradient_precision: Not Set >> unmodified

    • base_model_default_dtype: bf16 >> fp32

androflux-v11-3600
Open Source ModelUnlimited UsageLLMs.txt
API PlaygroundAPI Documentation

Input

androflux-v11-3600

Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.

Output

Idle

Unknown content type

Related Models

Discover similar models you might be interested in

View all Models
Jim Daly Art Style (Unofficial) - Flux - version 1.0
ModelsLab

Jim Daly Art Style (Unofficial) - Flux - version 1.0

Open Source Model
SpongeBob SquarePants Ultimate (PONY/FLUX/SDXL/SD) - SpongeBob Flux
Popular
ModelsLab

SpongeBob SquarePants Ultimate (PONY/FLUX/SDXL/SD) - SpongeBob Flux

Open Source Model
I_Pomo Mix [Ipomo + NAI + Pony + artists etc.] - L1n3s v1.1 - Original
ModelsLab

I_Pomo Mix [Ipomo + NAI + Pony + artists etc.] - L1n3s v1.1 - Original

Open Source Model
Retro Dark Fantasy - v1.0 Illustration
ModelsLab

Retro Dark Fantasy - v1.0 Illustration

Open Source Model
Olympia Hill, Ladybug, Miraculous. Different models and attires. - Majestia (Flux)
ModelsLab

Olympia Hill, Ladybug, Miraculous. Different models and attires. - Majestia (Flux)

Open Source Model
Bright & Colorful Photos [Flux Dev] - V2
ModelsLab

Bright & Colorful Photos [Flux Dev] - V2

Open Source Model
The Arbiter - Flux v1
ModelsLab

The Arbiter - Flux v1

Open Source Model
[Flux]wlop+anime style from Nai3 - v0.3
ModelsLab

[Flux]wlop+anime style from Nai3 - v0.3

Open Source Model
AWPortrait-Flux-lora
ModelsLab

AWPortrait-Flux-lora

Open Source Model
Cinematic Vintage + Modern Christmas style F1D + XL + SD1.5 - Christmas F1D v1.0
ModelsLab

Cinematic Vintage + Modern Christmas style F1D + XL + SD1.5 - Christmas F1D v1.0

Open Source Model
Fkey style (Flux dev test version) - v1-512-booru
ModelsLab

Fkey style (Flux dev test version) - v1-512-booru

Open Source Model
high heels for Flux - v1.1
ModelsLab

high heels for Flux - v1.1

Open Source Model
Ivan Bilibin Style - FLUX
Popular
ModelsLab

Ivan Bilibin Style - FLUX

Open Source Model
Flux spirals of light / glow enhance - V1
ModelsLab

Flux spirals of light / glow enhance - V1

Open Source Model
Chromecore Style - FLUX - 7X - v1.0
ModelsLab

Chromecore Style - FLUX - 7X - v1.0

Open Source Model
Glowing Drawing - v1.1
ModelsLab

Glowing Drawing - v1.1

Open Source Model
Liminal Space in the 90s - 90s Liminal Spaces FLUX.D
ModelsLab

Liminal Space in the 90s - 90s Liminal Spaces FLUX.D

Open Source Model
Flux-loras (full package)-(updated) - furry_lora
Popular
ModelsLab

Flux-loras (full package)-(updated) - furry_lora

Open Source Model

AndroFlux - V11-3600 Readme

Changelog from v8 Configuration

  • MAX_NUM_STEPS: 10000 >> 30000

  • CHECKPOINTING_STEPS: 100 >> 200

  • TRAIN_BATCH_SIZE: 2 (unchanged)

  • GRADIENT_ACCUMULATION_STEPS: 1 >> 2

  • RESOLUTION: 1024 >> 512

  • LEARNING_RATE: 1.0 (unchanged)

  • OPTIMIZER: Prodigy (unchanged)

  • VALIDATION_GUIDANCE: 3.5 (unchanged)

  • VALIDATION_GUIDANCE_REAL: 1.0 >> 2.0

  • INSTANCE_PROMPT: Not Set >> "AndroFlux, "

  • TRAINER_EXTRA_ARGS:

    • base_model_precision: fp8-quanto (unchanged)

    • lora_rank: 8 >> 16

    • max_grad_norm: 0.01 >> 1.0

    • gradient_precision: Not Set >> unmodified

    • base_model_default_dtype: bf16 >> fp32