ComfyUI beginner friendly Krea 2 Text-to-Image Workflow with Easy Prompt Saver by Sarcastic TOFU

This is a very simple workflow that helps you to save your Krea 2 Text to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You will find all the saved prompt files that it generated with the images inside the Archive (.Zip) that has the workflow. Also with the Image Saver Simple node used here you may embed the workflow itself with each saved image or save the image and workflow for your work separately.

Developed by Krea AI, the Krea 2 (K2) foundation models are latent diffusion architectures designed specifically as "aesthetic-first" engines for creative professionals. While Black Forest Labs' Flux.2 [klein] is optimized for ultra-fast, compact footprints (ranging from 4B to 9B parameters) and local image editing, it notoriously struggles with correct human anatomy. Krea 2 overcomes this by prioritizing visual coherence and utilizing a highly specialized dataset that is captioned with immense aesthetic intention. Furthermore, Krea 2 inherently excels at character consistency because it natively supports blending up to 10 style and composition reference images, mapping latent attention across generations to prevent the anatomical breaking and "AI look" that occurs when pushing the lightweight Klein models.

You can download your necessary model files used in this workflow from HuggingFace and LORA from CivitAI (Details are mentioned below). Make sure you have latest enough ComfyUI installation and install any necessary nodes for for this workflow using ComfyUI manager and place the correct files in correct places. Also check out my other workflows for SD 1.5 + SDXL 1.0, Pony, WAN 2.1, WAN 2.2, MagicWAN Image v2, QWEN, HunyuanImage-2.1, HiDream O1, Ernie Image, KREA, Chroma, AuraFlow, NoobAI, Illustrious, Lumina2, Z-Image Turbo, Flux.2 Klein 9B & 4B, Flux.1 Dev and Kandinsky Image 5 Lite (T2I & I2I) models. Feel free to toss some yellow Buzz on other stuffs (LORAs, utilities, Datasets etc.) you like from me.

How to use this -

#1. Just select your desired Krea 2 model files first and

#2. set your desired image dimensions to start

#3. then input your desired image prompt.

#4. select how many images you want (Change the number besides the "Run" button)

#5. select image sampling methods, CFG, steps etc. settings

#6. finally press the run button to generate. That's it..

** LORA usage for this workflow is optional you can use it without any LORAs, use with 1 or 2 or any other number of LORAs, to add new LORAs press the L button on top to lunch LORA Manager on a new tab find your LORA and if you want to use that LORA just click the upward Kite button.

Required Files

===============

### Download Link for Krea 2 models -

++++++++++++++++++++++++++++++++++++++

I used the following models for this workflow on my computer with 8 GB VRAM and they worked very well -

https://huggingface.co/vantagewithai/Krea-2-Raw-GGUF/resolve/main/krea2_raw-Q2_K.gguf

https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/resolve/main/krea2_turbo-Q2_K.gguf

**All the example generations of this workflow have used the Turbo model but they can be reproduced with Raw on slower speed with not much quality improvements, since most Krea2 LORAs have been trained for Turbo I used the Turbo model as default for this workflow.

Alternatively if you have higher VRAM (16 GB or above) you can try models from here -

https://huggingface.co/Comfy-Org/Krea-2/tree/main

### Download Link for Krea 2 Text Encoder -

++++++++++++++++++++++++++++++++++++++++++++

This is the one I used -

https://huggingface.co/Comfy-Org/Krea-2/resolve/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors

Alternatively you may use this GGUF one on weaker system -

https://huggingface.co/gguf-org/krea-2-gguf/resolve/main/qwen3vl_4b-iq4_xs.gguf

### Download Link for Krea 2 Text Encoder -

++++++++++++++++++++++++++++++++++++++++++++

This is the one I used (Exact same one from Qwen Image, if you have use QWEN Image you may already have it) -

https://huggingface.co/Comfy-Org/Krea-2/resolve/main/vae/qwen_image_vae.safetensors

Alternatively you may use this GGUF one on weaker system -

https://huggingface.co/gguf-org/krea-2-gguf/resolve/main/pig_wan_vae_fp32-f16.gguf

LORAs used on this workflow -

++++++++++++++++++++++++++++++

These are some of the LORAs (Not all) I used with this workflow, besides these I mentioned I tested this workflow without any LORAs and with some of my own and many other most popular LORAs for Krea 2 on CivitAI. I can say that this workflow can generate the most quality outputs (I mean the NSFW stuffs besides other stuffs) simply with proper selection of Krea 2 LORAs and bit of prompt krafting. I have found Krea 2 doing very well with anatomy and character consistency compared to other models.

Realism Enhancer Krea2 -

https://civitai.red/models/2727284/realism-enhancer-krea2?modelVersionId=3065628

Krea 2 Official LORAs -

https://civitai.red/models/2726235/krea-2-official-loras?modelVersionId=3064426

Krea2 AIO NSFW LoRA -

https://civitai.red/models/2732306/krea2-aio-nsfw-lora?modelVersionId=3071904