Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
This is a very simple workflow that helps you to save your Kandinsky 5 Lite Text to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You...
Profil d'exécution
Description de la source
This is a very simple workflow that helps you to save your Kandinsky 5 Lite 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 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 last example image 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.
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
This ComfyUI workflow is for Kandinsky 5 Lite text-to-image generation and saving generation data. It accepts model files, image dimensions, a text prompt, image count, and sampling settings, and can produce generated images plus human-readable .txt metadata files.
Select the Kandinsky 5 Lite text-to-image model files, set image dimensions, enter a prompt, choose the image count and sampling settings, then run the workflow.
The workflow can place saved prompt files with the images in an Archive (.Zip). Image Saver Simple may embed the workflow with each saved image or save the image and workflow separately.
Inputs include model files, image dimensions, a text prompt, image count, sampling method, CFG, and steps.
Outputs include generated images and .txt files containing generation metadata.
Use a sufficiently recent ComfyUI installation, install the needed nodes through ComfyUI Manager, and put the model files in the correct folders.
Named node packs include comfyui-simple_readable_metadata-sg, comfyui_memory_cleanup, comfy-image-saver, and ComfyUI_JPS-Nodes.
They also include comfyui-easy-use, comfyui-kjnodes, and comfyui-image-saver.
Listed model files include 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.
Before running, adjust image dimensions, image count, sampling method, CFG, and steps.
Guidance: For text-to-image generation, use the Kandinsky 5 Lite text-to-image model; its text-to-image and image-to-image models are separate.
Suggestion · non vérifié
Guidance: The instructions name kandinsky5lite_t2i.safetensors for text-to-image, while the model file named Kandinsky/kandinsky5lite_i2i.safetensors appears separately; verify which checkpoint your setup expects before running.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 194 downloads · Type Workflows · Base model Other
You can download your necessary Kandinsky 5 Lite Text-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 Text-to-Image model files first and now
#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..
** 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.
Estimation des besoins VRAM
Estimation indisponible
Les tailles des fichiers du modèle ne sont pas encore suffisamment complètes pour calculer cette exigence.
Exigences
Exigences 12VAE · Hugging Face · Comfy-Org/z_image_turbo
Text encoder · Hugging Face · Flux/clip_l.safetensors
Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf
Non résoluText encoder · Hugging Face · Hunyuan/Dumpling-Qwen2.5-VL-7B.Q2_K.gguf
Kandinsky/kandinsky5lite_i2i.safetensors
Non résoluCheckpoint · Hugging Face · Kandinsky/kandinsky5lite_i2i.safetensors
VAE · Hugging Face · Z-Image_Turbo/UltraFlux-v1_VAE.safetensors
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
