jejunepixels/Hammershoi-Flux3-LoRA

Hammershoi FLUX 3 Klein LoRA

Prompt

a wide view of a woman seen from behind looking at a window, hmrsh style

Prompt

a wide view of a woman in a dark dress seen from behind in a sparse hallway, a dark overcoat on a coat stand, a door ajar to an adjacent room, hmrsh style

Prompt

a wide view of a sparse room with a large dark iron stove, an open doorway beyond revealing a window with an overcast sky and bare branches, hmrsh style

Prompt

a close-up of a young woman with blue eyes in a dark dress, hmrsh style

Prompt

a wide view of two women in dark clothing seated at a round table with a white tablecloth, a silver candlestick at the centre, white teacups before each woman, hmrsh style

Prompt

a wide view of a woman in a dark dress in profile seated at a wooden desk, a glass oil lamp lit at the corner, a quill pen in her hand over an open book, hmrsh style

Prompt

a wide view of a woman in a dark dress seated in a bentwood rocking chair beside a window, a folded newspaper in her lap, white muslin curtains, hmrsh style

Prompt

a wide view of a dark table with a white ceramic bowl near a window, a harbour with dark sailing ships visible through the window glass, hmrsh style

Prompt

a wide view of a figure in dark clothing small against a wide orange ploughed field, bare autumn trees on a low horizon, a pale overcast sky, hmrsh style

Prompt

a wide view of a neoclassical building with an arched gateway across an empty square under a pale sky, hmrsh style

Prompt

a wide view of a dark room with a round table bearing two lit candles in tall silver candlesticks, a glass decanter and two wine glasses beside them, hmrsh style

Prompt

a wide view of a woman in a dark dress silhouetted at a window, a white roller blind half-drawn behind her, a white mug on a dark desk at left, hmrsh style

Prompt

a wide view of a sparse room with a dark wood square piano, a tall window showing grey church spires above red tiled rooftops, hmrsh style

Prompt

a medium view of a woman in a dark dress seated beside a cast-iron stove, hands folded in her lap, a brass poker beside the stove, hmrsh style

Prompt

a wide view of a man in a dark jacket and white shirt collar seated at a dark desk, a brass inkwell and an open leather-bound ledger before him, a bookcase behind, hmrsh style

Prompt

a wide view of a sparse room with a framed black-and-white photograph on a pale wall, a dark wooden bench below it, a folded dark jacket on the bench, hmrsh style

Prompt

a wide view of a woman in a dark dress seated on a chaise longue, a small side table with a white ceramic vase, single window light from the left, hmrsh style

Prompt

a medium view of a woman in a dark dress in profile beside a windowsill, a small potted cactus on the sill before a pale overcast sky, hmrsh style

Prompt

a medium view of a woman in a dark dress seated at a dark desk, a small portable speaker and a single book on the shelf behind her, hmrsh style

Prompt

a wide view of a woman facing the viewer, behind her an open window with a view of a river and a cloudy sky, hmrsh style

Prompt

a wide view of a woman in a dark dress seated at a round table, a white damask tablecloth, a silver candlestick with a burning candle before her, hmrsh style

Prompt

a close-up of two female hands holding a candle, in the background an open window with a view of a moonlit river, hmrsh style

Prompt

a wide view of a woman in a dark dress seated at a desk, a single lamp casting a circle of light on a closed laptop, deep shadow around her, hmrsh style

Prompt

a wide view of a low green landscape under a wide bank of white cumulus clouds, hmrsh style

Prompt

a close-up of a closed silver laptop on a dark wooden desk, a white ceramic mug with black coffee beside it, a pale wall behind, hmrsh style

Prompt

A medium view of a woman standing beside a tall window in a quiet room, looking out. Daylight from the window falls across her shoulder and the wall behind her. A bare wall and a plain wooden floor. hmrsh style

Prompt

a row of buildings on a quiet street, hmrsh style

Prompt

an empty room with a door, hmrsh style

Prompt

a woman standing by a window, hmrsh style

Prompt

A wide view of a row of buildings along a quiet street, with no people or traffic. Flat facades with rows of tall windows, a paved road in the foreground, sky above the rooftops. hmrsh style

Prompt

A wide view of an empty room with a single closed door in the far wall and a tall window on the left. Daylight falls across the wooden floorboards. Bare walls, a simple skirting board, no furniture. hmrsh style

Model description

A LoRA fine-tuned on FLUX 3 Image Klein Base to generate images in the quiet, introspective style of Danish painter Vilhelm Hammershøi (1864–1916). Characterized by muted palettes, sparse domestic interiors, solitary figures, and profound stillness.

You don't need to describe the style in your prompt. The gallery prompts contain no style words, only the framing, the subject and the trigger phrase. The gallery was picked from 60 images of 30 prompts with two seeds each, so expect some results to be weaker. See also the Flux1 version, the Flux2 version and the Ideogram 4 version.

The same prompt and seed in each row, on prompts with no style words.

Trigger words

End your prompt with hmrsh style.

Recommended settings

Parameter	Value
Base model	FLUX 3 Image Klein Base
Steps	30
Guidance	3.5
LoRA scale	1.0
Resolution	1024×1024 (square)

LoRA scale 1.5 moves further from the original image and closer to the muted colours of the paintings, but it can look grainy. All testing used these settings at 1024×1024.

Usage

The base model is gated, so accept its license on the model page and log in with your Hugging Face token first. Install Diffusers from GitHub, along with peft. This is the code the gallery images were made with:

import torch
from diffusers.modular_pipelines import Flux3AutoBlocks

blocks = Flux3AutoBlocks()
blocks.sub_blocks.pop("prompt_upsampler", None)  # send the prompt as typed
pipe = blocks.init_pipeline("black-forest-labs/flux-3-image-klein-base")
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")

pipe.load_lora_weights(
    "jejunepixels/Hammershoi-Flux3-LoRA",
    weight_name="Hammershoi_flux3_klein.safetensors",
    adapter_name="hammershoi",
)
pipe.set_adapters(["hammershoi"], adapter_weights=[1.0])
pipe.guider = pipe.guider.new(guidance_scale=3.5)

image = pipe(
    prompt="a woman standing by a window, hmrsh style",
    width=1024,
    height=1024,
    num_inference_steps=30,
    generator=torch.Generator("cuda").manual_seed(42),
    output="images",
)[0]
image.save("hammershoi.png")

Prompt tips

The model was trained on short captions. Following this format gives the best results:

[framing] of [subject and setting], hmrsh style

For example: a medium view of a woman in a dark dress seen from behind, hmrsh style

Framing — start with one of these, the openings used in the training captions:

• a wide view of — full scene with environment
• a medium view of — figure from waist up
• a close-up of — head, hands or objects
• an extreme close-up of — fine detail crops
• a full-figure view of — head to toe

Subject — describe what is in the scene and where, in plain words. You don't need to add oil on canvas or other style words.

Light — plain descriptions of the light worked in testing: single window light from the left, a pale overcast sky, lit candles, a single lamp casting a circle of light.

What worked best — sparse rooms with doorways, stoves and windows, women in dark dress seen from behind or in profile, portraits, and quiet harbours, fields and buildings.

What worked less well — bright modern rooms and modern objects tend to stay closer to a photograph, and hands are sometimes malformed.

Short prompts and full scene descriptions both work. The full descriptions gave cleaner pictures when tested without the LoRA, and Black Forest Labs recommends them for this model.

Limitations and biases

• Testing was small. The final checkpoint was tested on 36 prompts with one or two seeds, at guidance 3.5 and 1024×1024 only. Other image shapes and settings are untested.
• It can add a fake signature. About a quarter of the images we checked had a small signature or monogram in a lower corner, sometimes resembling "Hammershøi" or hmrsh, because the training paintings are signed. Those images were left out of the gallery. Check your images, and don't present them as works by Hammershøi.
• Modern subjects stay closer to a photograph. Bright modern rooms and objects such as a laptop are only partly painted.
• Hands are sometimes malformed.
• Some setups are untested. This has not been tried with the Klein prompt upsampler, with the distilled FLUX 3 Image Klein checkpoint, or in ComfyUI.
• It can change your subject. It doesn't only change the surface. At scale 1.0 a modern figure can become a woman with pinned-up hair in a dark period dress, even if you didn't ask for that.
• Narrow subject range. It was trained on one painter's work: sparse Danish interiors, landscapes and portraits. People in these paintings are mostly European, often women in dark period dress, so expect results to lean that way unless your prompt says otherwise.
• Captions are not perfect. They were shortened by script from captions that were drafted by Claude and reviewed by hand. The result was spot-checked, with some fixed by hand.

Training details

Base model	black-forest-labs/flux-3-image-klein-base
Training images	288 crops, the same images as jejunepixels/Hammershoi-Ideogram4-Dataset, which lists each source
Captions	Framing and subject only, at most 15 words, no style words
Sources	SMK Open · Wikimedia Commons
Training tool	AI Toolkit
Training hardware	RTX 4090
Trigger phrase	hmrsh style
LoRA rank	32
Steps	2000
Learning rate	0.0003
content_or_style	content
Caption dropout	0.3, leaving only the trigger phrase
Sampler	Flowmatch
dtype	bf16

License

These weights are a fine-tuned derivative of FLUX 3 Image Klein Base, modified by jejunepixels, and are released under the FLUX Kommunity License v.1.0. Any rights to use them are granted directly by Black Forest Labs to you under that license. It permits non-commercial use, and commercial use of outputs by Qualifying Users, subject to its terms. A copy of the license and the required NOTICE are included in this repo.

This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Kommunity License. Copyright Black Forest Labs Inc. IN NO EVENT SHALL BLACK FOREST LABS INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

The weights are provided as is, with no warranty of any kind, and with the same disclaimers and limits of liability as Sections 5 and 6 of the license.

This is a community project. It is not an official Black Forest Labs product and has not been endorsed, approved or validated by Black Forest Labs. Images made with this LoRA are AI-generated.

Training images were collected from SMK Open and Wikimedia Commons. The Wikimedia files trace back to museums, auction houses and other sources. Vilhelm Hammershøi died in 1916 and his paintings are in the public domain; check the source of a reproduction before reusing it.

Download model

Download the weights in the Files & versions tab.