FLUX.1 - CivArchive (CivitAI Archive)

FLUX.1 - Schnell

NSFW

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:

Reference implementation and sampling code are available in a dedicated Black Forest Labs GitHub repository.

Credits: Developed by Black Forest Labs.

FLUX

by Black Forest Labs: https://blackforestlabs.ai

Description

FAQ

Comments (10)

yepeishengAug 4, 2024

CivitAI

2070S_8G + 16G RAM / 640*1088，可以出图，但是速度很慢（特别是最后的 VAE Decode，系统几乎失去响应），连续生成两张图片后，系统崩溃重启了（估计出现了内存交换错误？）

2070S_8G + 16G RAM / 640*1088, It can generate images, but the speed is very slow (especially in the final VAE decode, where the system almost loses response). After generating two consecutive images, the system crashes and restarts (presumably due to a memory swap error)

GeekDLAug 4, 2024· 2 reactions

I have a 1080 8VRAM + 32GB RAM working fine so far, had to switch from xformers to flash attention this gave me a 20% speed over xformers, but you need to use the torch dev nightly packages, hope this help you improve, maybe you need to add more ram and use fallback system policy RAM memory on the nvidia control panel look for 3D settings and then choose prefer system fallback OR activate it on Program Settings.

jeriffAug 4, 2024· 1 reaction

买个4090吧，以后玩AI模型，24G显存起步的。

capitalcon

Author

Aug 4, 2024· 1 reaction

@jeriff I just uploaded 11gb DEV version, check it out

mukasidoraemon849Aug 4, 2024

Please, what am I doing wrong? I gathered everything I needed and put it where it should be.

Error occurred when executing CheckpointLoaderSimple: ERROR: Could not detect model type of: C:\sd\Data\Packages\ComfyUI\models\checkpoints\flux1_devFP8110GBKijai.safetensors File "C:\sd\Data\Packages\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\sd\Data\Packages\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\sd\Data\Packages\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\sd\Data\Packages\ComfyUI\nodes.py", line 518, in load_checkpoint out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings")) File "C:\sd\Data\Packages\ComfyUI\comfy\sd.py", line 518, in load_checkpoint_guess_config raise RuntimeError("ERROR: Could not detect model type of: {}".format(ckpt_path))

yepeishengAug 4, 2024· 2 reactions

@mukasidoraemon849 update your comfyui

capitalcon

Author

Aug 4, 2024· 2 reactions

@mukasidoraemon849 Make sure u have ComfyUI updated for Flux Nodes, check official ComfyUI guide at https://comfyanonymous.github.io/ComfyUI_examples/flux/

mukasidoraemon849Aug 4, 2024

Comfyui is the latest version, but an error occurs. I'll read the explanation carefully again. thank you.

yepeishengAug 6, 2024· 1 reaction

After updating ComfyUI again, a smaller VAE model was used and VAE Decode (Tiled) nodes were used. Finally, the graph can be continuously generated without system crashes. Thank you to the experts from all walks of life for their continuous efforts.

MagicalEroticaAug 20, 2024

@yepeisheng Your system was probably using the pagefile. I'm glad I bought that extra ram back in the day.

Checkpoint

Flux.1 S

by capitalcon

Download (Beta) View on CivitAI

Details

Downloads

1,079

Platform

CivitAI

Platform Status

Available

Created

8/2/2024

Updated

5/14/2026

Deleted

Files

flux1_schnell.safetensors

Size:

22.15 GB

SHA256:

9403429e0052277ac2a87ad800adece5481eecefd9ed334e1f348723621d2a0a