Skip to content

EthenEthenEthen

Open Source Model Profile · Muapi

swarm-flux

swarm-flux is a text-to-image LoRA from Muapi for FLUX.1-dev. According to the model card, it uses mad-swrm as trained word with MUAPI API usage.

Publisher
Muapi
Task
text-to-image
Model type
Unknown
License
openrail++
Library
diffusers
Publication status
Accepted · not indexed

Model overview

swarm-flux is published by Muapi as a diffusers text-to-image LoRA. Hub tags list black-forest-labs/FLUX.1-dev as base model and adapter. According to the model card, it is a Swarm FLUX variant for Flux.1 D with mad-swrm as trained word and MUAPI API usage.

Recorded capabilities

FLUX.1-dev base tags

Hub tags list black-forest-labs/FLUX.1-dev as base model and adapter; the card names Flux.1 D as base.

mad-swrm trained word

According to the model card, mad-swrm is the trained word.

MUAPI API usage

According to the model card, generation uses the MUAPI flux_dev_lora_image API with key header and a JSON payload including 1024x1024 sizing.

Use cases in the source record

  • Text-to-image generation on the tagged FLUX.1-dev base using the documented mad-swrm word.
  • MUAPI API workflows that call flux_dev_lora_image with key authentication and sized image requests.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No parameter count was extracted for this LoRA record.
  • Training steps, rank, and dataset details were not extracted; only base and trained-word notes come from the publisher card.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Muapi/swarm-flux

Captured: Unknown. Processed: 2026-09-07T19:36:06.911790+00:00.

Swarm FLUX Base model : Flux.1 D Trained words : mad-swrm 🧠 Usage (Python) 🔑 Get your MUAPI key from muapi.ai/access-keys import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = { "Content-Type" : "application/json" , "x-api-key" : os.getenv( "MUAPIAPP_API_KEY" )} payload = { "prompt" : "masterpiece, best quality, 1girl, looking at viewer" , "model_id" : [{ "model" : "civitai:869678@973354" , "weight" : 1.0 }], "width" : 1024 , "height" : 1024 , "num_images" : 1 } print (requests.post(url, headers=headers, json=payload).json())

F001F002F003F004F005F006F007F008