Model reference · open weights
Flux is an open-weight image model from StableDiffusionVN. Flux (BF16) weighs 16.3 GB; the smallest configuration that runs it is RTX 4090 24 GB.
Summary of the StableDiffusionVN/Flux model card, 2026-10-01
What it is
| Released by | StableDiffusionVN |
|---|---|
| Released | 2024-08-04 |
| VRAM | 16.3 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | tight | 23.4 GB |
| RTX 4090 24 GB | tight | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Youtube:
Colab Training Lora: Comfy Workflow:
=> Text-img
=> Img-img
=> Inpaint
=> Schnell Text-img
=> Schnell Text-img-upscale
=> Lora Tester
=> Lora Text to img
=> Lora Text to img Upscale
=> Schnell Lora Text to img
=> Union Controlnet
=> Hyper 8Steps Lora Upscale
Comfy Node:
Comfy NF4 Support: https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4
Comfy GGUF Support: https://github.com/city96/ComfyUI-GGUF
Comfy Instant Union Controlnet Support: https://github.com/EeroHeikkinen/ComfyUI-eesahesNodes
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face. Its model loader takes .safetensors files: replace it with Unet Loader (GGUF) and choose this model's file there.
# on your rented machine (the ssh line is on its page in the console)
# the GGUF loader nodes, once per machine
git clone https://github.com/city96/ComfyUI-GGUF /opt/ComfyUI/custom_nodes/ComfyUI-GGUF
pip install -r /opt/ComfyUI/custom_nodes/ComfyUI-GGUF/requirements.txt
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (24.0 GB)
get StableDiffusionVN/Flux Checkpoint/Flux_schnell_v1-fp8.safetensors diffusion_models
get StableDiffusionVN/Flux Clip/t5-v1_1-xxl-encoder-Q4_K_S.gguf unet
get StableDiffusionVN/Flux Clip/t5xxl_fp8_e4m3fn.safetensors text_encoders
get StableDiffusionVN/Flux Vae/flux_vae.safetensors vae
get StableDiffusionVN/Flux Redux/sigclip_vision_patch14_384.safetensors clip_vision
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT