modelli/FLUX.1 - DEV FP8 - Kijai [11 GB]

FLUX.1 - DEV FP8 - Kijai [11 GB]

6/30/2025

8:10:24 AM

Parole Chiave e Tag Correlati

anime,modello base,capitalcon,cartoon,checkpoint,dev fp8 - kijai [11 gb],flux.1,flux.1 d,high-quality image generation,latent adversarial diffusion distillation,fotorealistico,realistico,rectified flow transformer

A glamorous woman with curly red hair wearing a sparkling vintage costume, red stockings, gloves, and high heels, swinging high with flowing red and pink plumes trailing behind her against a black background.

Strong female adventurer resting on a mossy rock by a clear waterfall in a lush tropical jungle, wearing tactical shorts, crop top, gloves, boots, and mirrored aviator sunglasses with a combat knife nearby

Bird's-eye view of a futuristic apartment complex with circular windows glowing orange, concrete walls, metal grills, minimalistic white sofa, and potted plants.

A regal white tiger with red stripes wearing ornate red and blue armor with golden filigree and a crown, holding a golden staff and polearm with swirling magical paint energy around.

A small green alien creature with large round eyes and wrinkled skin, resting on an open palm, captured in a vintage analog film style photo.

Realistic cyberpunk-style painting of a woman in a white sweater with '34' and bunny ears, standing next to a vintage mechanical robot with bunny ears.

A close-up of a modern owl with feathers resembling recycled reflective metal and glass discs, against an abstract background symbolizing ecology and renewal.

Highly detailed futuristic motorcycle with a sleek white aerodynamic body accented with orange, featuring a visible motor, digital dashboard, and smooth circular wheels on a light gray background.

Close-up top-down photo of a rectangular rusted metal object with a screen showing a planet, weathered blue-green paint, and red lettering 'AKZA MIARA SMA'.

Photo-realistic cybernetic humanoid robot with rusted cream and dark blue mechanical armor, glowing orange energy orbs in eyes and chest, against dark background.

Anime style illustration of a blonde WWII bomber pilot screaming inside a damaged cockpit with bullet holes and mechanical parts exposed, against a stormy sunset sky with flak explosions outside.

A shirtless man wearing a fedora sits on a moss-covered white rhinoceros, fishing by a misty forest pond at dawn with golden sunlight filtering through the trees.

Parametri Consigliati

steps

1 - 4

Suggerimenti

Follow official ComfyUI installation, workflow, and usage at https://comfyanonymous.github.io/ComfyUI_examples/flux/

Reference implementation and sampling code are available on Black Forest Labs GitHub repository: https://github.com/black-forest-labs/flux

Punti Salienti della Versione

float8_e4m3fn weights of:

https://huggingface.co/black-forest-labs/FLUX.1-dev

License: flux1-dev-fp8.safetensors falls under the FLUX.1 [dev] Non-Commercial License.

Version credit to: Kijai

Sponsor del Creatore

Check out the official ComfyUI workflow and installation guide for FLUX.1: https://comfyanonymous.github.io/ComfyUI_examples/flux/

Explore the FLUX.1 model and code on Black Forest Labs GitHub: https://github.com/black-forest-labs/flux

Visit Black Forest Labs official website: https://blackforestlabs.ai

FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. It is trained using latent adversarial diffusion distillation, allowing it to generate high-quality images in only 1 to 4 steps. The model offers cutting-edge output quality and competitive prompt following, matching the performance of closed-source alternatives.

Released under the Apache 2.0 license, the model can be used for personal, scientific, and commercial purposes. You must provide proper attribution, indicate if changes were made, and not use the model or its derivatives for unlawful or harmful activities.

Follow official ComfyUI installation, workflow and usage: https://comfyanonymous.github.io/ComfyUI_examples/flux/

Key Features:

High-quality image generation from text descriptions.

Efficient image generation in 1 to 4 steps.

Out-of-Scope Use

The model and its derivatives may not be used

In any way that violates any applicable national, federal, state, local or international law or regulation.
For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content.
To generate or disseminate verifiably false information and/or content with the purpose of harming others.
To generate or disseminate personal identifiable information that can be used to harm an individual.
To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.
To create non-consensual nudity or illegal pornographic content.
For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation.
Generating or facilitating large-scale disinformation campaigns.

Usage: