← Workflows

SDXL + LoRA Image

Text → Image

Text-to-image with an SDXL checkpoint plus a character/style LoRA — a consistent trained identity or style rendered from a prompt.

sdxl_lora8 GB VRAMLoRA support

Calling it

FlixML has no generate button: you tell your agent what you want and it calls the API on your install. The id is what names this workflow.

POST /api/image/generate
{
  "workflow": "sdxl_lora",
  "prompt": 0,
  "checkpoint": 0,
  "lora_name": 0
}

Parameters

promptstringrequired

Comma-separated tags and short phrases, not a sentence — same tag syntax as sdxl_base: subject first, atmosphere last, `(term:1.2)` to weight a term, roughly 75 tokens of content before the tail stops pulling. What differs here is the LoRA. Most character and style LoRAs fire on a trigger word, and without it in the prompt the LoRA loads and does close to nothing: put the trigger at the front, then describe only what the LoRA does not already carry — pose, clothing, setting, light. Describing the face a character LoRA was trained on fights it. The LoRA's model page is where the trigger word is stated; there is no way to read it off the file.

checkpointstringrequired

SDXL checkpoint model filename

lora_namestringrequired

LoRA filename

negative_promptstringdefault

What to steer away from, same tag syntax. Keep it to defects you actually see — 'blurry, low quality, extra fingers, watermark'. An oversized negative eats guidance and flattens the image.

widthintegerdefault 832
heightintegerdefault 1216
seedintegerdefault 42
stepsintegerdefault 28
cfgfloatdefault 7
samplerstringdefault dpmpp_2m
schedulerstringdefault karras
lora_strengthfloatdefault 0.8

LoRA strength (model and clip)

Your install is the source of truth: GET /api/workflows returns these parameters as they are on your machine.

Same input, different job

FLUX.2 dev + LoRA Image

Text-to-image with FLUX.2 plus one or more trained character LoRAs — a consistent identity rendered at high fidelity from a prompt.

FLUX.2 Klein Image

Text-to-image with FLUX.2 Klein 4B. High-fidelity stills from a prompt, with two optional LoRA slots.

SDXL Base Image

Text-to-image with an SDXL checkpoint. General-purpose still generation from a prompt — no character LoRA, no source image.

Text Logo / Wordmark

Typeset exact text as a logo/wordmark using a real TTF font (ComfyUI AddLabel node) — NOT diffusion. Use this whenever the output must spell an exact string (a handle, brand, wordmark) that diffusion models garble. Renders instantly, GPU-light, lands in the gallery like any generation.