Language

Flux Dev and its LoRAs: the complete guide to FLUX.1 [dev] and LoRA add-ons

FLUX.1 [dev], released by Black Forest Labs on August 1, 2024, became the base for the largest LoRA ecosystem in open image generation. This guide explains the model, what a LoRA is and how it works, how trigger words, weights and stacking behave, and which kinds of LoRA are worth knowing, with examples from published LoRA model cards.

Grid of sample images rendered by FLUX.1 dev, including lettering, a crocheted duck and a gingerbread house
Official FLUX.1 [dev] samples. Image: Hugging Face (Black Forest Labs)

Log in and try FLUX.1 [dev]

FLUX.1 [dev] runs in Prism, SpyGlass, Vector, Unified Editor and PirateDiffusion with the <flux-dev> base, and any Flux.1 LoRA you import is called with <lora:shortcode:weight>.

Log in to My Graydient

Graydient plans are compatible with FLUX.1 [dev]

Run FLUX.1 [dev] alongside more than 30,000 open image and video models on flat-rate GPU, with no credits and no per-image fees.

View plans

Already a member? Log in to My Graydient.

What is FLUX.1 [dev]?

Black Forest Labs launched the FLUX.1 suite on August 1, 2024 in three variants: [pro] through its API, [dev] as open weights, and [schnell] as a fast Apache 2.0 model. According to the announcement and model card, FLUX.1 [dev] is:

Recommended Flux Dev settings

SettingValueNotes
Guidance3.5The value in Black Forest Labs’ Diffusers example
StepsAbout 20 to 28Diffusers example uses 50; LoRA authors commonly publish 24
Resolution1024×1024 and similarDiffusers example size
Negative promptNot usedGuidance-distilled; describe what you want instead

Flux reads natural sentences. Describe the scene, add the LoRA trigger word, and leave Stable Diffusion keyword lists behind.

What is a LoRA?

LoRA stands for low-rank adaptation, a technique introduced by Hu et al. in 2021. Instead of retraining a model's billions of weights, training freezes the base model and learns a pair of small low-rank matrices for selected layers. The result is a compact file, typically tens to a few hundred megabytes, that adds one capability on top of the base: a style, a character, a product, a camera look, or a fix.

Trigger words

Most LoRAs are trained with a trigger word, a phrase attached to every training caption. Putting it in your prompt activates the effect. The trigger is listed on the LoRA page, and it is often deliberately unusual so it does not collide with ordinary vocabulary. The tarot LoRA below uses in the style of TOK a trtcrd tarot style.

A tarot-card illustration of an office cubicle
Image: Hugging Face (multimodalart/flux-tarot-v1)
A tarot-card illustration of a dog at a table
Image: Hugging Face (multimodalart/flux-tarot-v1)
Prompt with trigger words (flux-tarot-v1 model card)
a work cubicle in the style of TOK a trtcrd, tarot style

Weights

The weight (or scale) sets how strongly the LoRA applies. It is the setting that fixes most poor renders.

Minimalist logo of a leaf containing a cat silhouette
Image: Hugging Face (Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design)
Minimalist logo of a figure whose shadow forms the letter A
Image: Hugging Face (Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design)
Prompt with trigger words (Logo Design LoRA model card, recommended scale 0.8)
wablogo, Minimalist, Leaf and cat, logo,

Stacking LoRAs

Several LoRAs can be combined, for example a film-look LoRA with a detail LoRA. Each keeps its own weight. Keep stacked LoRAs at about 0.7 or lower so they do not fight, and change one weight at a time while testing.

The LoRA types worth knowing

Photographic looks

Film-stock and camera LoRAs change colour science, grain and light. The Koda LoRA, triggered by flmft style, imitates a Kodachrome film look.

View of a desert highway through a car window with a light leak
Image: Hugging Face (alvdansen/flux-koda)
A hiker on a ridge above misty mountains
Image: Hugging Face (alvdansen/flux-koda)
Prompt with trigger words (flux-koda model card)
Road trip, view through car window of desert highway, light leak effect, flmft style

Illustration styles

Style LoRAs are the largest category. Vector Journey blends illustrated characters into realistic scenes; its trigger is a whole sentence.

Cartoon-style boy playing video games in a realistic living room
Image: Hugging Face (Shakker-Labs/FLUX.1-dev-LoRA-Vector-Journey)
Cartoon-style pianist in an ornate concert hall
Image: Hugging Face (Shakker-Labs/FLUX.1-dev-LoRA-Vector-Journey)
Prompt with trigger sentence (Vector Journey model card)
A cartoon-style boy playing games in his living room, artistic style blends reality and illustration elements.

Design and layout

Logo, icon and template LoRAs constrain the output to a graphic format, as with the Logo Design LoRA above.

Instructional and technique

Some LoRAs teach a format rather than a style. How2Draw (CC0) produces step-by-step drawing sheets with the trigger How2Draw.

Step-by-step drawing sheet of an owl
Image: Hugging Face (glif/how2draw)
Step-by-step drawing sheet of a Yorkshire terrier
Image: Hugging Face (glif/how2draw)

Characters, products and people

Subject LoRAs teach one specific face, character or product from 15 to 30 images. Use them only for subjects you have the right to depict.

Control and utility

Black Forest Labs released official FLUX.1 Canny and Depth LoRAs in November 2024 for structural control. Detail and realism LoRAs, such as Shakker-Labs' Add Details, sharpen texture without changing style.

Using Flux LoRAs on Graydient

On Graydient, a LoRA in your library is called with a tag of three parts, the word lora, its ShortCode and a weight, followed by the base model ShortCode. In PirateDiffusion (Telegram) and Vector (Discord) the command looks like this; replace the example ShortCodes with the ones in your library:

Graydient command: one LoRA on Flux Dev
/render a work cubicle in the style of TOK a trtcrd, tarot style <lora:your-tarot-lora:0.8> <flux-dev> /steps:24 /guidance:3.5 /size:768x1024
Graydient command: two stacked LoRAs on Flux Dev
/render Road trip, view through car window of desert highway, light leak effect, flmft style <lora:your-film-lora:0.6> <lora:your-detail-lora:0.5> <flux-dev> /steps:24 /guidance:3.5

Prism accepts the same tags at the end of a message, and SpyGlass and the Unified Editor take the tag in the prompt field after you pick the Flux base. The full walkthrough is in how to use a Flux LoRA on Graydient.

Compatibility

BaseFLUX.1 LoRAs work?
FLUX.1 [dev] and FLUX.1 fine-tunesYes
FLUX.1 [schnell], FLUX.1 Krea [dev]Generally, with weaker results on schnell
FLUX.2 [dev], FLUX.2 [klein]No; use FLUX.2 LoRAs
FLUX 3 Image KleinNo; use FLUX 3 LoRAs
Krea 2, Qwen-Image, AnimaNo; separate architectures

Limitations

How to use FLUX.1 [dev] on Graydient

You are all set. FLUX.1 [dev] runs in Prism, SpyGlass, Vector, Unified Editor and PirateDiffusion with the <flux-dev> base, and any Flux.1 LoRA you import is called with <lora:shortcode:weight>. Use the Log in to My Graydient button at the top of this page, open your app, and paste a prompt from this guide.

  1. Choose a Graydient plan. Graydient plans are compatible with FLUX.1 [dev].
  2. FLUX.1 [dev] runs in Prism, SpyGlass, Vector, Unified Editor and PirateDiffusion with the <flux-dev> base, and any Flux.1 LoRA you import is called with <lora:shortcode:weight>.
  3. Paste a prompt from this guide and render. Plans are flat-rate, so there are no credits or per-image fees.

Workflow details: How to use a Flux LoRA on Graydient · How to train a Flux LoRA · UltraReal Flux workflow · Import Civitai models

Graydient plans are compatible with FLUX.1 [dev]

Run FLUX.1 [dev] alongside more than 30,000 open image and video models on flat-rate GPU, with no credits and no per-image fees.

View plans

Already a member? Log in to My Graydient.

FLUX.1 [dev] FAQ

What is FLUX.1 [dev]?

FLUX.1 [dev] is a 12-billion-parameter rectified-flow transformer from Black Forest Labs, announced on August 1, 2024. It is an open-weights, guidance-distilled model derived from FLUX.1 [pro].

What is a Flux LoRA?

A LoRA (low-rank adaptation) is a small add-on file that teaches a base model one thing, such as a style, a character, a product or a camera look, without changing the base model itself. It only works with the model family it was trained for.

What is a trigger word?

A word or phrase the LoRA was trained with. Including it in the prompt activates the effect; many style LoRAs do little without it. The LoRA page lists it.

What weight should I use for a Flux LoRA?

Start at the weight the LoRA author recommends; 0.8 is a common default. Lower it in steps of 0.1 if the image looks over-processed, raise it slightly if the effect is weak.

Can I stack several LoRAs?

Yes. Add two or three LoRAs, each with its own weight, and keep each around 0.7 or lower so they do not compete.

Do FLUX.1 LoRAs work on Flux 2, Flux 3 or Krea 2?

No. FLUX.1 LoRAs work on FLUX.1 [dev] and FLUX.1-based checkpoints. FLUX.2, FLUX 3 and Krea 2 each need LoRAs trained for them.

Is Flux Dev compatible with Graydient plans?

Yes. Graydient plans are compatible with FLUX.1 [dev] and imported Flux.1 LoRAs from ModelTrends, Civitai or Hugging Face.

Sources

Images are example outputs published by the model authors and the community on Hugging Face and the ComfyUI blog, used with credit. They were not made on Graydient. Specifications are as stated by the model developers at release.

More model guides

← All Graydient blog posts