GGUF Diffusion

Model

required

Select a .gguf / .safetensors model…

--diffusion-model for a standalone diffusion model file (Flux, SD3.5, Wan…); --model for an all-in-one checkpoint (SD1.x/SDXL).

--vae

Optional VAE…

--tokenizer-pack

Optional tokenizer pack folder…

Text Encoders

optional

No external text encoders. Needed for Flux / SD3.5 / Wan-style models (--clip_l, --t5xxl, --llm, …).

Additional Models

optional

No additional models (ControlNet, TAESD, upscaler, PhotoMaker, …).

Image Inputs

optional▾

Feed an initial, mask, end, control, or reference image — for img2img, inpainting, first/last-frame video, ControlNet guidance, or Kontext-style editing.

--init-img

Initial image…

--mask

Mask image…

--end-img

End-frame image (flf2v)…

--control-image

Control image…

Reference images `--ref-image`

Prompt

Positive prompt -p Negative prompt -n optional

Generation

CFG Scale

1.0 for turbo/flow models, 7.0 for standard SD.

Steps

4 for turbo/flow models, 20–30 for standard SD.

Width Height

Seed (-1 = random) Batch Count

Sampling Method Schedule

Flags

Flash attention --diffusion-fa Verbose -v

Low VRAM / memory (off by default)

Memory-map model --mmap Offload weights to CPU --offload-to-cpu CLIP on CPU --clip-on-cpu VAE on CPU --vae-on-cpu ControlNet on CPU --control-net-cpu

Output

Command

Edit manually

Model

Text Encoders

Additional Models

Image Inputs

Reference images `--ref-image`

Prompt

Generation

Flags

Output

Command

Save current setup

Saved workflows

Generated images

Hardware

Engine log

Model

Text Encoders

Additional Models

Image Inputs

Reference images --ref-image

Prompt

Generation

Flags

Output

Command

Save current setup

Saved workflows

Generated images

Hardware

Engine log

Reference images `--ref-image`