--- license: other license_name: krea-2-community-license license_link: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf base_model: - krea/Krea-2-Turbo base_model_relation: quantized pipeline_tag: text-to-image library_name: gguf tags: - gguf - comfyui - krea-2 - text-to-image - quantized - lora-merge language: - en --- # Krea-R-Turbo ## Try Krea-R-Turbo in SPACES! [![Open in Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Krea--R--Turbo-orange)](https://huggingface.co/spaces/realrebelai/Krea-R-Turbo) Full Weight and GGUF quants of custom merge of Krea-2-Turbo and 2 of my style LoRAs at specific strength values. Displays a heavy focus on photorealistic portraits to achieve high grade aesthetics while also retaining Krea-2s sharp detail! This is a **derivative** of [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo): LoRA-merged, then quantized. It is not the original checkpoint.
example 0
example 1
example 0
example 0
example 2
example 3
example 4
example 5
example 6
example 7
example 8
example 9
example 10
example 11
example 12
example 13
example 14
example 15
## Quants Pick by how much VRAM you can spare for the diffusion model (leave room for the text encoder + VAE). Sizes are approximate — see the **Files** tab for exact numbers. | File | Type | ~Size | Notes | |------|------|-------|-------| | `Krea-R-Turbo-Q8_0.gguf` | Q8_0 | ~14 GB | Near-lossless. For 16 GB+ cards or offload. | | `Krea-R-Turbo-Q6_K.gguf` | Q6_K | ~11 GB | Excellent quality, hard to tell from Q8. | | `Krea-R-Turbo-Q5_K_M.gguf` | Q5_K_M | ~9.4 GB | Great quality/size balance. | | `Krea-R-Turbo-Q4_K_M.gguf` | Q4_K_M | ~8.0 GB | **Recommended all-rounder.** 12 GB cards, or 8 GB with offload. | | `Krea-R-Turbo-Q3_K_M.gguf` | Q3_K_M | ~6.4 GB | **Best pick for 8 GB VRAM.** Small quality trade. | | `Krea-R-Turbo-Q2_K.gguf` | Q2_K | ~5.5 GB | Tightest fit. Visible degradation but usable. | On an 8 GB card (e.g. RTX 3070), Q3_K_M or Q2_K fit most comfortably alongside the VAE and text encoder. Larger quants still run via ComfyUI's `--lowvram` / block-swap offload — just slower. --- ## Usage in ComfyUI **Place the files:** | File | Folder | |------|--------| | `Krea-R-Turbo-QX.gguf` (this repo) | `ComfyUI/models/unet/` (or `diffusion_models/`) | | `qwen3vl_4b` text encoder | `ComfyUI/models/text_encoders/` | | `qwen_image_vae.safetensors` | `ComfyUI/models/vae/` | The text encoder (Qwen3-VL 4B) and VAE (Qwen-image VAE) are the standard Krea 2 companions and can be pulled from the ComfyUI repack: [`Comfy-Org/Krea-2`](https://huggingface.co/Comfy-Org/Krea-2). **Wire it up:** load the GGUF with the **Unet Loader (GGUF)** node, feed it the Qwen3-VL text encoder and Qwen-image VAE, and sample as normal Krea 2 Turbo. ### Recommended sampling Krea 2 Turbo is a distilled, few-step model: - **Steps:** ~8 - **Guidance:** CFG-free — set CFG to `1.0` (no negative prompt), or guidance `0` - **Sampler / scheduler:** `er_sde` + `simple` works well (or `euler` + `simple`) - **Resolution:** up to 2048², 1024–1280 sweet spot on 8 GB No positive/negative CFG split is needed; this checkpoint was distilled without it. --- ## Requirements - ComfyUI (recent build with Krea 2 support) - [RealRebelAI/ComfyUI-GGUF_KREA-2](https://github.com/RealRebelAI/ComfyUI-GGUF_KREA-2) custom node - Qwen3-VL 4B text encoder + Qwen-image VAE (from [`Comfy-Org/Krea-2`](https://huggingface.co/Comfy-Org/Krea-2)) This repo contains the **diffusion model (transformer) only** — it will not generate anything on its own without the VAE and text encoder above. --- ## License & attribution These weights are a derivative of **Krea 2 Turbo** © Krea.ai, Inc., and remain governed by the **Krea 2 Community License Agreement** and the **Krea Acceptable Use Policy** — exactly as the original model. See the license: [LICENSE.pdf](https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf). In the event of any conflict, the Krea Acceptable Use Policy and Krea 2 Community License control. **Deployer obligation:** if you serve or redistribute this model, the license requires you to implement content-filtering or equivalent review to prevent generation or distribution of unlawful or policy-violating content. Report harmful or illegal outputs to `safety@krea.ai`. Upstream: - Base model: [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo) (distilled from [`krea/Krea-2-Raw`](https://huggingface.co/krea/Krea-2-Raw)) - ComfyUI repack (VAE / text encoder): [`Comfy-Org/Krea-2`](https://huggingface.co/Comfy-Org/Krea-2) - GGUF tooling based on city96's [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) The merge and quantization are RealRebelAI's work; the underlying model rights belong to Krea.ai, Inc. --- ## Credits Merged, quantized, and released by **RealRebelAI**. - GitHub: [github.com/RealRebelAI](https://github.com/RealRebelAI) - Hugging Face: [huggingface.co/realrebelai](https://huggingface.co/realrebelai) If these are useful, a like on the repo helps others find them. Issues with loading go on the [ComfyUI-GGUF_KREA-2](https://github.com/RealRebelAI/ComfyUI-GGUF_KREA-2) tracker.