Saltar al contenido
ModelPublicadoExterno
Descargar

FLUX.2 Klein Base 9B DF11

flux-non-commercial-license

TipoUNetModelo baseblack-forest-labs/FLUX.2-klein-base-9BVersiónCcalidad

Fuente del modelo

Tipo
UNet
Tamaño del archivo
11,5 GB
Modelo base
black-forest-labs/FLUX.2-klein-base-9B
Versión
vflux-2-klein-base-9b-DF11-old
Actualizado
2 oct 2026
Descargas
89
Fuente
Hugging Face

Descripción de la fuente

Note: It appears to me that the DF11 FLUX.2 [klein] models are bugged, often producing outputs that are slightly different from BF16 outputs. I have confirmed that the DF11 weights are indeed 100% identical to BF16 weights when decompressed, so this should be some bug with inferencing that I am struggling to diagnose. In the meantime, I recommend using the this model with the default KSampler node, instead of the CustomSamplerAdvanced node. Also if you have the VRAM to run this model in BF16, I recommend to use the newly added DFloat11Decompressor node to load this model instead. This node fully decompresses the DF11 weights into BF16 weights, and outputs a model that is 100% identical to the Load Diffusion Model node. I apologize for the inconvenience, as I investigate this issue.

Fuentes

1 fuente
Hugging FacePrincipalVersión 87126e0ae3a2d56c190517000897497945f64fc3
huggingface.co/mingyi456/FLUX.2-klein-base-9B-DF11-ComfyUI/tree/87126e0ae3a2d56c190517000897497945f64fc3

Verificado 2 oct

Artefactos del modelo

1 artefacto

flux-2-klein-base-9b-DF11-old.safetensors

safetensors · 11,5 GB · SHA-256 7118642cb7df…2deb · Hugging Face

Descargar

Extractos de fuentes

2 extractos

--- license: other license_name: flux-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md language: - en pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - black-forest-labs/FLUX.2-klein-base-9B base_model_relation: quantized --- ## Note: It appears to me that the DF11 FLUX.2 [klein] models are bugged, often producing outputs that are slightly different from BF16 outputs. I have confirmed that the DF11 weights are indeed 100% identical to BF16 weights when decompressed, so this should be some bug with inferencing that I am struggling to diagnose. In the meantime, I recommend using the this model with the default KSampler node, instead of the CustomSamplerAdvanced node. Also if you have the VRAM to run this model in BF16, I recommend to use the newly added DFloat11Decompressor node to load this model instead. This node fully decompresses the DF11 weights into BF16 weights, and outputs a model that is 100% identical to the Load Diffusion Model node. I apologize for the inconvenience, as I investigate this issue.

Source context: 89 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/FLUX.2-klein-base-9B-DF11-ComfyUI