Update 2026-07-05: Krea 2 Turbo v2.0 workflow added
PhotoFlow Krea 2 v2.0
Upscaling has been improved in version 2.0. There are now presets for the settings (sampler, scheduler, and denoise settings) . This allows upscaling to be performed in pixel space to achieve upscales with minimal denoising, resulting in smoother backgrounds that closely resemble the original image. In addition, the euler_ancestral_cfg_pp sampler in combination with the linear_quadratic scheduler is now recommended for high image quality. For fast generation, euler_ancestral with simple can still be used. There are also now filters to correct the colors of the final image, which can become flat due to repeated sampling.
⚠️ Note that the latest version 0.27.0 of ComfyUI (July 2027) is required to use the fast int8 models.
Update 2026-07-02: Krea 2 Turbo v1.0 workflow added
PhotoFlow Krea 2 v1.0
Krea 2 Turbo is the new king of realism and is suitable for both SFW and NSFW content. This workflow is simple, super fast, and optimized for realism.
⚠️ Note that the latest version 0.27.0 of ComfyUI (July 2027) is required to use the fast int8 models.
Update 2026-03-30: Qwen-Image-2512 Nunchaku v1.0 workflow added
PhotoFlow Qwen-Image-2512 Nunchaku v1.0
Qwen-Image-2512 offers exceptional prompt comprehension and delivers outstanding output quality. However, this comes at the cost of very long generation times due to the model's size and the large number of processing steps required. A practical solution in this workflow is to use a heavily quantized Nunchaku FP4 version, which maintains surprisingly high quality. When combined with an 8-step Lightning LoRA, generation speed improves dramatically while image quality remains excellent.
⚠️ Nunchaku requires a few additional setup steps. Please follow the instructions provided in the workflow.
Update 2026-03-21: Flux.2 klein 9B v1.1 workflow added
PhotoFlow Flux.2 klein 9B v1.1
Version 1.1 is simply a hotfix that resolves an issue with an incorrect calculation of the tile size in the Refiner step. Additionally, the EasyLoraStack has been replaced by the Power Lora Loader. The group bypass for all additional steps now also takes the previews into account accordingly.
Update 2026-03-04: Flux.2 klein 9B v1.0 workflow added
PhotoFlow Flux.2 klein 9B v1.0
Flux.2 klein 9B is a fast, 4‑step model supporting image generation up to 4 MP. The workflow starts with a recommended 2 MP base image, followed by optional face refinement and SeedVR2 upscaling to 5 MP for added fine detail. A subsequent refinement step removes SeedVR2 artefacts and enables optional upscaling up to 16 MP. A subtle touch of film grain completes the process, enhancing realism.
Update 2025-12-07: Z-Image-Turbo v2.0 workflow added
PhotoFlow Z-Image-Turbo v2.0
Version 2.0 introduces an optional Refiner and FaceDetailer, along with a recommended set of LoRAs designed to enhance photorealism and overall image quality.
⚠️⚠️⚠️
Make sure you're using ComfyUI version 0.3.76 or newer, since earlier versions contained a bug that affected the correct application of Z-Image-Turbo LoRAs.
Also ensure your SeedVR2 node is up to date, as a previous issue causing visual artifacts has been fixed.
⚠️⚠️⚠️
♥️♥️♥️
A huge thank you to all the creators of the LoRAs recommended in version 2.0. Your work makes this level of quality possible!
All images in the gallery were generated using the same set of LoRAs with identical strength settings, so in most cases no additional tweaking is required 🙂.
Special thanks to Danrisi (NiceGirls UltraReal, Lenovo UltraReal), aip0pp (PhotoReal BetterNudes), HackAfterDark (After Dark), DirtMcGirt (psxZStyle - Photography Style Lora), ConflictX (35mm Photo), and oleshevakatya (Movie Wide Angle).
♥️♥️♥️
Update 2025-11-29: Z-Image-Turbo workflow added
PhotoFlow Z-Image-Turbo
Z-Index Turbo is super fast, can generate images in 2 megapixel resolution without upscaling, and focuses on realism, so no LoRAs are required.
Update 2025-11-23: Qwen workflow added
PhotoFlow Qwen
Until now, I had been hesitant to create a workflow for Qwen because, although its image quality is outstanding, the generation times can be very long when aiming for maximum quality. The Lightning LoRA helped reduce waiting times significantly, but using it alone led to a quality drop that didn’t meet my standards. However, by combining multiple LoRAs - including the 8 Steps Lightning LoRA - with a new upscaling process using SeedVR2, I have finally achieved a level of quality that satisfies me.
I have also released a separate workflow dedicated solely to upscaling images using SeedVR2. You can find it here.
Update 2025-10-12: Chroma workflow added
PhotoFlow Chroma HD Flash
After Danrisi released the awesome Lenovo UltraReal LoRA, I gave Chroma another shot because the images looked super promising. And I gotta say, Chroma HD is amazing! Chroma needs about 50 steps in standard mode for awesome results, and even with an RTX 5090, that's too long of a wait for me. Fortunately, there is a Chroma Flash LoRA that achieves great results with just a few steps. With CFG 1.0, the time per step is halved again!
Update 2025-08-23: Wan 2.2/2.1 T2I workflow added
PhotoFlow Wan T2I
Wan 2.1 and Wan 2.2 are video models that can also be used to create high-resolution images. Due to the impressive quality, I decided to create a dedicated workflow for them. Wan 2.2 was released during the development of this workflow. Fortunately, Wan 2.2 is even better and can be used like the Wan 2.1 model, including compatibility with most Wan 2.1 LoRAs. Style LoRAs, in particular, work very well. SageAttention with Triton is supported but not required, and the Lightning LoRA is used to ensure fast generation of high-resolution images. Instructions on how to set up and use the workflow are included within the workflow itself.
PhotoFlow XL
This SDXL ComfyUI workflow has been developed to generate realistic photos with a focus on people.
The version 2.0 is not restricted to the use of the DMD2 Speed LoRA. The workflow works just as well without it ♥️.
The default settings and comments in the workflow are geared towards DMD. Accordingly, you only need to adjust the CFG, sampler, scheduler and steps for a non-DMD use 🙂. These values are a good start for a generation without the DMD LoRA:
KSampler
CFG: 3.5 (2.5 - 5.5)
Sampler: dpmpp_sde_gpu
Scheduler: normal
Steps: 25
FaceDetailer
CFG: 3.5 (2.5 - 5.5)
Sampler: dpmpp_sde_gpu
Scheduler: karras
Steps: 18
Recommended Checkpoints
The following checkpoints are particularly suitable:
SFW
epiCRealism XL: https://civarchive.com/models/277058?modelVersionId=1920523
HelloWorld XL: https://civarchive.com/models/43977/leosams-helloworld-xl
Juggernaut XL: https://civarchive.com/models/133005/juggernaut-xl
RealVisXL 5.0: https://civarchive.com/models/139562?modelVersionId=789646
NSFW
Jib Mix Realistic XL: https://civarchive.com/models/194768?modelVersionId=1809082
DonutsDeliveryMix: https://civarchive.com/models/605283?modelVersionId=1739105
Lustify: https://civarchive.com/models/573152?modelVersionId=1094291
Analog Madness SDXL: https://civarchive.com/models/408483/analog-madness-sdxl-realistic-model
Big Love XL2: https://civarchive.com/models/897413?modelVersionId=1464711
XXX-Ray v1.1: https://civarchive.com/models/1064836?modelVersionId=1305584
NSFW (DMD included)
GonzaLomo (Unity/Real XL DMD): https://civarchive.com/models/1513492/gonzalomo-xlfluxpony
Lustify ENDGAME DMD2: https://civarchive.com/models/573152?modelVersionId=1099200
XXX-Ray DMD2: https://civarchive.com/models/1064836?modelVersionId=1624818
Installation
ComfyUI Manager Installation
https://github.com/ltdrdata/ComfyUI-Manager?tab=readme-ov-file#comfyui-manager
Installation of Missing Nodes
Missing nodes in this workflow are highlighted in red. To install them, open the ComfyUI Manager and click on the “Install Missing Custom Nodes” button.
⚠️‼️ComfyUI-KJNodes needed‼️⚠️
It it may happen that the ComfyUI-KJNodes are not included in the list of missing nodes. Simply install the ComfyUI-KJNodes via ComfyUI Manager > Custom Nodes Manager.
After the installation, restart ComfyUI and refresh the browser page.
Further information and tips on configuration can be found in the workflow in the INFO node.
TL;DR
The workflow was developed and tested with a NVIDIA RTX 4080 (16 GB VRAM) and 96 GB RAM.
Leave a positive review, if you like the workflow 😊.
Description
PhotoFlow Z-Image-Turbo v1.0
This text-to-image workflow is specifically designed to generate images with a strong emphasis on realism. To further enhance the resolution and quality significantly, the SeedVR2 video upscaler is ideal, as it refines finer details without compromising the original texture integrity.
FAQ
Comments (12)
Thanks for the Zimage! Beyond impressed with it so far.
Let me say your work is pure brilliance. The level of detail and your capacity to not let anything escape you is just unreal. I love your work.
That said, unfortunately with this workflow I keep getting OOM, right by the SEEDVR2 ( Allocation on device: This error means you ran out of memory on your GPU) I have a 5090 V24 Laptop and don't understand why this happens. Any pointers as to why or what I need to tweak would be appreciated. Thanks again!
The default values for SeedVR2 are designed for maximum hardware requirements, as I have 32 GB VRAM and 96 GB RAM and unfortunately I don't know what values are designed for more common VRAM sizes such as 24 GB or 16 GB. There are many parameters that affect VRAM usage. First of all, you should make sure that you don't have any other software open that uses VRAM, such as Photoshop, VLC, etc. It's best to check the hardware utilization while testing changes. In Windows, you can do this in the Task Manager under the Performance tab. Tiling is most likely to solve the problem, but it has the disadvantage that the seams between the tiles are often visible. First, I would look at the console logs. They will tell you exactly where the OOM problem occurs. Increase the blocks_to_swap value and activate swap_io_components. Check the logs to see how the utilization changes. Switching to an fp8 model may also be the solution on its own. Reduce Target Image Megapixels to 6, for example. If that's still not enough, activate tiling. Maybe start with 2048 as the tile size. Reduce it further if that's not enough. The value should be divisible by 64. How to solve OOM problems is also explained quite well here: https://www.youtube.com/watch?v=MBtWYXq_r60&t=530s
Thank you for taking the tine to reply. I am floored by your generosity.
Seriously, the attention to detail in everything you do does not go unnoticed, this includes how you put together your workflows. Bar none.
But I forgot to mention, your sense of humor and imagination! The lady unsuspectingly jumping into the wide-opened jaws of a great white all whilst a nuclear missile deployed in the background makes chaos itself look stolid! LOL
I played it back a few times as if it were some lascivious rewind on cable. Chuckling.
Anyhow, thanks for your help.
I got it to work!
I used zImageTurboQuantized_fp8ScaledE4m3fnKJ.safetensors and it didn't complain.
Maybe not the res that you had intended, but it worked.
Thank you again :)
YOU are very much appreciated!
z-image does not work for me, keep getting
clip input is invalid.
The file might be corrupted. Please download it again, select "lumina2" as the type, and make sure ComfyUI is up to date.
Having the same problem. After checking with GPT, it pointed towards a torch problem, which is already difficult to handle on a 5070. Hopefully the next update will make it easier!
Edit: just updated ComfyUI and it's working now.
@Anon31272 Maybe it helps to install the latest NVDIA driver and CUDA 13: https://developer.nvidia.com/cuda-downloads
@ai839 Update. Newbie mistake: I couldn't use Z Image because I hadn't updated ComfyUI. It's solved now, and the workflow works perfectly thanks to your excellent explanation. May your internet connection never lag for your generous contribution!
I was not ready for the quality and detail. Holy crap! Thank you and great job!
I've tried dozens of wf's for z image and so far this is my favorite. Couldn't get it to work off the bat, but luckily it's explained fairly well and once I figured out the offloading it looked amazing. I usually adapt most wf's to my taste and but this one is pretty perfect as it is. I tried adding a facedetailer before the film grain to improve the likeness of the lora I'm using but somehow its making it a lot worse.
Ty for ur hard work brother, godspeed