8 steps, CFG 1, a picture in about six seconds on a 5090.

(Text to Image + Image to Image)

Two ways to run it, chosen with one number. There is a single blue INPUT box near the left:

1 = text to image. Type a prompt, press Run.

2 = image to image. Load your own picture, press Run.

Two samplers sit behind that box with the denoise already correct for whichever you pick, so there

is one knob and not two. The half you did not choose never runs — nothing to mute, nothing wasted.

At CFG 1 the negative prompt does nothing at all. Not a little — nothing. That is what CFG 1 means, and it is why the box is left empty in this file. If you want a negative prompt to work, take the Extended file instead.

WHAT IT RUNS ON

Our own Krea 2 build, and it is free — every build on that page opens for any signed-in member, no code and no card. You also need the Krea 2 text encoder and VAE from the official Comfy-Org

repository, and the ComfyUI Impact Pack from ComfyUI Manager (that is the switch, and it is the only extra thing this file needs).

Watch the VAE:

it is qwen_image_vae, NOT wan_2.1_vae. Use the wrong one and nothing warns you — no

error, no red border. It runs every step, decodes, saves a picture, and the picture is coloured

static.

THERE ARE THREE OF THESE WORKFLOWS

Turbo

(8 steps, CFG 1, ~6s, no negative prompt),

Extended

(16 steps, CFG 2, ~22s, negative works),

Base

(20 steps, CFG 3, ~46s, negative works).

They are genuinely different files, not three presets of one. Start with Turbo if you just want to see something.

Everything

Links to all three files, the model, the folder each file goes in, and the settings: grab it here

The model on its own:

Is here

Workflow, settings and write-up are mine. Krea 2, its text encoder and VAE are Comfy-Org's. The

switch node is from the ComfyUI Impact Pack by ltdrdata.