Introduction to the FLUX Model

August 1stOpen SourceWenshengtu ModelWe have reached a big milestone.Black Forest Laboratory(One has completed$31 millionThe 12B Wenshengtu model of the seed round series financing) is as follows:FLUXShocking release. This is the largest open source model of text-to-image so far. This is also the current high-quality text-to-image model. The FLUX.1 text-to-image model suite defines a new state-of-the-art level for text-to-image synthesis, setting new benchmark standards in image detail, prompt following, style diversity, and scene complexity. Striking a balance between accessibility and model capabilities, FLUX.1 has three variants: FLUX.1 [pro], FLUX.1 [dev], and FLUX.1 [schnell]:

• • FLUX.1 [dev] : The base model, open source and with a non-commercial license, for the community to build on top of it. https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/main
• • FLUX.1 [schnell] : A stripped-down version of the base model, a distilled version,23.8 GB, which can run up to 10 times faster. Apache 2 license. https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/flux1-schnell.sft
• • FLUX.1 [pro] : Official closed-source version, which can be used through API services. API address: https://replicate.com/black-forest-labs/flux-pro, https://docs.bfl.ml/

FLUX Model Evaluation

FLUX.1 [pro] and [dev] surpass popular models in every aspect, such as Midjourney v6.0,DALL·E 3 (HD)and SD3-Ultra: Visual quality, cue following, size/aspect variation, typography, and output diversity.FLUX.1 [schnell] is the most advanced few-step model to date, outperforming not only its comparable competitors but also strong non-distilled models like Midjourney v6.0 and DALL·E 3 (HD). The FLux models are specifically fine-tuned to maintain the entire output diversity during pre-training. They offer the potential for significant improvements over the current state-of-the-art, as shown below.

All FLUX.1 model variantsBoth support 0.1 and 2.0 megapixel in multiple aspect ratios and resolutions, as shown in the following example.

Examples of aspect ratios and resolutions supported by FLUX.1

in additionBlack Forest LaboratoryThe team mentioned that after the Flux model, the plan is to furtherEntering the field of cultural videoIn the near future we may have a major milestone release in the field of Vincent Video.

Flux Model Experience

Flux ComfyUI Installation

The latest version of ComfyUI already supports the operation of Flux model. You only need to update ComfyUI to the latest version. ComfyUI official documentation: https://comfyanonymous.github.io/ComfyUI_examples/flux/.

• • Model download requiredFlux1-schnell.sftPlace in directoryComfyUI/models/unet/ Download address: https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/flux1-schnell.sft. If the video memory is less than 24, try to use the 8-bit quantization version: https://hf-mirror.com/maximsobolev275/flux-fp8-schnell/resolve/main/flux1-schnell_fp8_unet.safetensors?download=true
• • Need to download VAE modelae.sftPlace in directoryComfyUI/models/vae Download address: https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.sft
• • Need to download T5 text encoding modelt5xxl_fp8_e4m3fn.safetensorsPlace in directoryComfyUI/models/clip Download address: https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main

Workflow interface

This workflow has been published toLIBLIBAIIt can be freely downloaded and used at: https://www.liblib.art/modelinfo/4e5daf0cf50542199e5bd3b5174b168e.

01. Bull Witch

A Korean beautiful idol with horns and beautiful face, in a black outfit in the style of James Jean, against a flat red background, with cinematic lighting, in a minimalistic design, with dark contrast

02. Light and Shadow

masterpiece, best quality, 1girl ((pure gradient background, )), long hair, floating hair, blush, looking at viewers, happy, ((front)),(upper body), (studio light), soft light, dark style , night style

03. Cheongsam

(look at viewer:2), 1 girl, solo,chinese dress, cheongsam, earrings, Chinese roll, smile, lips, light green background,sfw,8k high definition, 35 mm film photography, photo realistic, insanely detailed, intricate, elegant, best quality, ultra-detailed, masterpiece, finely detail, highres, 8k wallpaper

04. Anime

(Animation style:1.3), a female character with long, flowing hair that appears to be made of ethereal, swirling patterns resembling the Northern Lights or Aurora Borealis. The background is dominated by deep blues and purples, creating a mysterious and dramatic atmosphere. The character's face is serene, with pale skin and striking features. She wears a dark-colored outfit with subtle patterns. The overall style of the artwork is reminiscent of fantasy or supernatural genres

05. Photographic composition - full body shot + frontal perspective

front view, full body shot),1girl, solo, realistic, chinese girl,(cowboy shot:1.2), real life location,tiny pink shirts, midriff, short skirt, smile, cute,, thin short waist, large pelvis,, (high quality:1.4), (photorealistic:1.6), 8k, uhd, highres, absurdres, professional photo, highly detailed, detailed skin

06. Lotus

A lotus flower, close to the sun, triple exposure, fantastic illustrations

07. Minions

a group of six minions in a yellow boat on a river in Paris, France. The boat is floating on the water, with the Eiffel Tower in the background. The minions are all facing the same direction and appear to be happy and excited. are all wearing blue overalls and have big smiles on their faces. The river is lined with buildings on both sides, and there are pink and purple flowers floating in the water. The sky is blue and the overall mood of the image is cheerful and playful .

08. Big Cat

hug cat,1girl,solo,(1 orange Giant cat:1.3),red dress,indoor,the cat stands, the girl is next to the cat, 8k high definition, 35 mm film photography

09. Ice Sculpture-Literary Forum

three statues of Chinese characters standing on a stage with a blue background. The statues are made of ice and are intricately carved with detailed features. The characters are dressed in traditional Chinese clothing, with long robes and hats. They are standing in a line, facing towards the left side of the image. The figure on the left is holding a book in his hands, while the figure in the middle is standing with his hands clasped in front of him. All three figures have a serious expression on their faces and appear to be in a contemplative pose. The background is a gradient of blue and white, with rays of light shining down on the figures

10. Beach

Beautiful woman in white summer dress standing at the beach, dress and hair flying in the wind, sun glasses, summer day, sunny, detailed sand textures, piercing eyes, perfect delicate face, perfect lips, Oil Painting, expressive brushwork, luminous color palette , and delicate details, Miki Asai Macro photography, close-up, hyper detailed, trending on artstation, sharp focus, studio photo, intricate details, highly detailed, by greg rutkowski