ChrisColeTech/krea2-turbo-edit-GGUF

Krea 2 Turbo (+ Identity Edit) — GGUF build

8-step distilled text-to-image and identity-preserving instruction editing — ≈35 s per 1024² image on an RTX 5090, guidance-free.

What this repo is: the Krea 2 Turbo Edit denoiser (identity LoRA baked in) as GGUF at three quant tiers plus a scaled-FP8 build, with the Qwen3-VL-4B text encoder and Qwen-Image VAE it needs — weights only, not a retrain. The settings below are the values these weights are actually run with day to day.

Supported modes: txt2img, img2img, edit (identity-preserving, 1–2 reference images)

---

Samples

**prompt:** `a red apple on a rustic wooden table beside a window, soft daylight, fine skin texture and wood grain, studio photograph, sharp focus` — 1024×1024, 8 steps, guidance 0.0, seed 12345	**prompt:** `portrait of an older fisherman with a weathered face, natural window light, shallow depth of field, photorealistic` — 1024×1024, 8 steps, guidance 0.0, seed 99
**prompt:** `a rain-slicked Tokyo street at night, neon signs reflecting in puddles, cinematic, 35mm photograph` — 1024×1024, 8 steps, guidance 0.0, seed 1234

---

Identity Edit

The signature mode. One reference image plus a plain-language instruction — the subject's identity, pose, lighting and scene survive; only the instruction changes. No mask, no inpainting region.

**reference** — the seed-99 portrait above, fed back as the edit source	**edit instruction:** `put a red knitted beanie hat on his head` — 8 steps, seed 7, ref_boost 1.0, grounding 768 px	**edit instruction:** `make it rain outside the window, wet glass with raindrops` — 8 steps, seed 7, ref_boost 1.0, grounding 768 px

---

img2img

Conventional strength-based restyling also works. One source (generated by this same build), three prompts, identical settings.

**source** — txt2img output of this build (`a dramatic mountain landscape at golden hour, snow-capped peaks, alpine lake reflection, photorealistic, 35mm photograph`, seed 42)	**img2img prompt:** `An oil painting of a dramatic mountain landscape at sunset, thick impasto brushstrokes` — 1024×1024, 8 steps, **strength 0.75**, seed 42	**img2img prompt:** `A watercolor painting of a mountain valley at dawn, soft wet-on-wet washes` — 1024×1024, 8 steps, **strength 0.75**, seed 42	**img2img prompt:** `A detailed pencil sketch of a mountain landscape in warm sepia and sanguine tones` — 1024×1024, 8 steps, **strength 0.75**, seed 42

---

Files used to generate

Component	File	Size	Download
Transformer	krea2_turbo_edit-Q4_K_M.gguf	7.26 GB	Link
Text Encoder	qwen3vl_4b_fp8_scaled.safetensors	5.24 GB	Link
Vae	qwen_image_vae.safetensors	254 MB	Link

---

⚠ Must use the updated GGUF Loader ⚠

In comfy:

• Open the ComfyUI Manager
• Change the channel to "Channel (remote)"
• and search for comfyui-gguf-loader

Use the workflow Link

Recommended settings

Parameter	Production value	Meaning
width	1024	Output width in pixels
height	1024	Output height in pixels
steps	8	8 min, 16 maximum
guidance	1.0	always use 1.0 for turbo variants

---

Notes and gotchas

• guidance 1.0 is correct. This is a fully guidance-distilled build; the text conditioning arrives through the Qwen3-VL encoder, not CFG. Raising guidance is not the lever for prompt adherence.
• The identity LoRA is baked into this denoiser (turbo_edit weights). There is no separate LoRA file to apply; plain txt2img and img2img use the same weights.
• Edit mode wants an instruction, not a description — put a red beanie on his head, not a man wearing a red beanie. Both reference identity and scene survive the edit (verified: same face, same window, same shirt across edits at seed 7).
• Upstream base model: Krea 2 Turbo Edit (Krea AI), Qwen-Image family architecture