Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This is a very simple workflow that helps you to save your Kandinsky 5 Lite Image to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You...
Runtime profile
Source description
This is a very simple workflow that helps you to save your Kandinsky 5 Lite Image 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 you may embed the workflow itself with each saved image or save the image and workflow for your work separately.
The Kandinsky-5.0-T2I-Lite model and its I2I variant are major milestones for the Russian AI landscape, having been developed by Sber AI and SberDevices in collaboration with the AIRI (Artificial Intelligence Research Institute). Released in November 2025, this 6-billion-parameter model family was specifically trained to excel at understanding Russian cultural concepts and linguistic nuances while remaining highly efficient for general use. The architecture, which utilizes a Cross-Attention Diffusion Transformer (CrossDiT) and dual text encoders like Qwen2.5-VL, allows it to produce high-resolution imagery at 1K quality with a focus on strong text rendering within the images themselves. This project stands as a central part of Russia's push into open-source generative foundation models, providing a lightweight yet powerful tool for both text-to-image and image-to-image synthesis that rivals much larger global counterparts. From my usage I can say that Kandinsky Image 5 Lite T2I & I2I models fit somewhere between Z-Image Base (or Flux.2 Klein) and very hunky Flux.2 Dev model in it's very unique way. I think this needs more attention, LORA and checkpoint trainings. Even without LORA this can do better unfiltered exposed anatomical details and skin textures (especially for European subjects) than Z-Image or Flux.2. (look at my example images generated with this workflow). I used a GGUF clip file I used once as an alternative second clip file than the one suggested by the developers of this model and even then it performed good with my 8GB VRAM OCULink connected eGPU. I provided more details below if you want to use full non-GGUF second clip file.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This ComfyUI workflow is for Kandinsky 5 Lite image-to-image generation: it takes a reference image, an image-to-image prompt, and model files, then can generate images and save metadata and prompt files as human-readable .txt files in an Archive (.Zip).
Select the Kandinsky 5 Lite image-to-image model files, choose a reference image, enter an image-to-image prompt, set generation controls, and run.
Inputs include Kandinsky 5 Lite image-to-image model files, a reference image, an image-to-image prompt, image count, sampling method, CFG, and steps.
Outputs include generated images, human-readable .txt metadata, and saved prompt files in an Archive (.Zip).
Image Saver Simple can embed the workflow with each saved image or save the image and workflow separately.
Use a sufficiently recent ComfyUI installation, install the necessary nodes with ComfyUI Manager, and place the required model files in the correct locations before use.
Suggestion
Listed node packs include comfy-image-saver, ComfyUI_JPS-Nodes, comfyui_memory_cleanup, and comfyui-easy-use.
They also include comfyui-image-saver, comfyui-kjnodes, and comfyui-simple_readable_metadata-sg.
Listed model files are ae.safetensors, Flux/clip_l.safetensors, Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf, Kandinsky/kandinsky5lite_i2i.safetensors, and Z-Image_Turbo/UltraFlux-v1_VAE.safetensors.
Set the image count beside Run, then choose the sampling method, CFG, and steps before running.
Suggestion · not verified
Use Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf as the listed GGUF text encoder, or choose a non-GGUF Qwen2.5 VL 7B text encoder from HunyuanVideo_1.5_repackaged as an alternative if it fits your system.
Suggestion · not verified
Use the Kandinsky 5 Lite image-to-image model for this workflow; its text-to-image and image-to-image models are separate, and using one for the other task may lead to unexpected outputs.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 200 downloads · Type Workflows · Base model Other
You can download your necessary Kandinsky 5 Lite Image-to-Image model used from HuggingFace (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, KREA, Chroma, AuraFlow, NoobAI, Illustrious, Lumina2, Z-Image Turbo, Flux.2 Klein and Flux.1 . Feel free to toss some yellow Buzz on stuffs you like.
How to use this -
#1. Just select your Kandinsky 5 Lite Image-to-Image model files first and now
#2. select your desired reference image to start
#3. then input your desired image to 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..
** Please note that Kandinsky 5 Lite Text-to-Image model and Kandinsky 5 Lite Image-to-Image model are two completely separate models and if you use one for other's task your outputs will not be as expected.
Required Files
===============
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Flux.1 Clip L Text Encoder (This is same as Flux.1, if you already have one you don't need to download again) -
Dumpling-Qwen2.5-VL-7B-GGUF Text Encoder (One used in the workflow) -
**alternatively you can use any one among these very big non-GGUF Qwen2.5 VL 7B text encoders from HunyuanVideo_1.5_repackaged repo ( https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/tree/main/split_files/text_encoders ) as your second clip file if you have very hunky GPU with 16GB or 24GB or 32GB GPU. See which one fits on your system.
++++++++++++++++++++++++++++++++++++++++++++++++++
(This is same as Z-Image VAE, if you already have one you don't need to download again) -
**alternatively you can use the UltraFlux VAE if you want from my CivitAI profile ( https://civitai.com/models/2245573/ultraflux-vae-mirrored-from-hugging-face-repo ) or other link mentioned on that post.
Estimated VRAM requirement
Estimate unavailable
Model file sizes are not complete enough to calculate this requirement yet.
Requirements
12 requirementsVAE · Hugging Face · Comfy-Org/z_image_turbo
Text encoder · Hugging Face · Flux/clip_l.safetensors
Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf
Not resolvedText encoder · Hugging Face · Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf
Kandinsky/kandinsky5lite_i2i.safetensors
Not resolvedCheckpoint · Hugging Face · Kandinsky/kandinsky5lite_i2i.safetensors
Z-Image_Turbo/UltraFlux-v1_VAE.safetensors
Not resolvedVAE · Hugging Face · Z-Image_Turbo/UltraFlux-v1_VAE.safetensors
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
