Kroma v0.2 β€” Krea 2 fine-tune (full model, quantized to ComfyUI formats)

Kroma is a fine-tune of Krea 2 by Lodestone-Rock. This repo contains quantized .safetensors files in various ComfyUI formats of the Kroma model.


Running in ComfyUI

1. Requirements

  • A recent ComfyUI with native Krea 2 support (update to the latest master).
  • The Krea 2 text encoder and VAE (the diffusion model is this repo β€” no separate base checkpoint needed).

2. Files to download

Place these in your ComfyUI folders:

What Where Notes
kroma-v0.2-turbo.safetensors ComfyUI/models/diffusion_models/ this repo
Krea 2 text encoder (Qwen3-VL) ComfyUI/models/text_encoders/ load with CLIPLoader type krea2
Krea 2 VAE ComfyUI/models/vae/

3. Sampling settings

The Krea 2 Turbo delta is merged in, so sample with Turbo settings:

Setting Value
Steps 8-12
Guidance (CFG) 1.0 – 1.5
Shift (mu) 1.15

These are the settings the Turbo checkpoint was distilled for; keep them for best results.

4. Workflow

  1. Load Diffusion Model β†’ select kroma-v0.2-turbo.safetensors.
  2. Load CLIP β†’ the Krea 2 text encoder, set type to krea2.
  3. Load VAE β†’ the Krea 2 VAE.
  4. KSampler β†’ steps / CFG / shift per the table above.
  5. Prompt and generate.

Minimal node chain:

Load Diffusion Model (kroma-v0.2) ─► KSampler ─► VAE Decode ─► Save Image
Load CLIP (krea2) ─────────────────► (clip)       β–²
Load VAE β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
Empty Latent / prompt ────────────────────────────►

5. Tips

  • If the output looks off, confirm the text encoder is loaded with type krea2 (Krea 2 expects a 12-layer Qwen3-VL stack) and that you're on a current ComfyUI.

Provenance

v0.2 was produced by continued full fine-tuning of the K2 (Krea 2) checkpoint behind Kroma v0.1 β€” without the rank-256 LoRA delta compression used for the v0.1 release β€” followed by merging the Krea 2 Turbo delta in as a rank-512 LoRA.

License

MIT β€” see LICENSE. Note that Krea 2 is governed by its own license; this fine-tune does not grant any rights to the base weights.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support