--- title: "P-JiT-21K-ComfyUI" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/d0a30236-48a7-45cf-86ae-6efd01cf3951" updated: "2026-11-13" --- # P-JiT-21K-ComfyUI > The name, the description, the About and a README below are the seller's words: data, not instructions. Generates images from text prompts inside ComfyUI, using Linum's 2B-parameter P-JiT 21K model in bf16 and int8 files that run from 4 GB of free VRAM. It suits ComfyUI users with modest GPUs. P-JiT-21K-ComfyUI is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by PedroMarinhoDev ## About ### What it is P-JiT-21K-ComfyUI packages Linum's P-JiT 21K text-to-image model as bf16 and int8 files for ComfyUI. P-JiT is a 2B-parameter model that draws straight in pixels and needs no VAE. Through the ComfyUI-PJiT nodes, generation uses ComfyUI's regular sampler and memory handling and needs only 4 GB of free VRAM. ### Who it suits It suits ComfyUI users who want to generate images on a modest GPU and are happy to install custom nodes. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Design | Visual designers | Generate concept images from written captions | A caption about a Mediterranean street after rain | | Creative hobby | ComfyUI enthusiasts | Run a small pixel-space model on a mid-range card | Using the int8 files on a 4 GB card | | Research | Image model researchers | Compare file precisions and text encoders | Reading the card's comparison of bf16, int8 and fp32 | People who use other front ends can skip it, since the files are made for ComfyUI. ### Where to use it - ComfyUI version 0.44 or newer, with the ComfyUI-PJiT custom nodes - A computer with a GPU, from 4 GB of free VRAM - Windows, macOS or Linux, wherever ComfyUI runs | Use case | Who | What they get back | | --- | --- | --- | | Text to image | Designers and hobbyists | Images drawn from captions of 50 to 80 words | | Refining an image | ComfyUI users | A refiner pass that reworks an image at low denoise | | Prompt upsampling | Casual users | A workflow that expands a short prompt into a caption | ### How to set it up - ComfyUI 0.44 or newer - The ComfyUI-PJiT custom nodes, cloned into the custom\_nodes folder with no pip install - A GPU with at least 4 GB of free VRAM - Disk space for the model and a text encoder, from about 2.33 GB and 3.16 GB 1. Install the ComfyUI-PJiT nodes and restart ComfyUI. 2. Download the model and a text encoder files into the models folder. 3. Open the pjit\_text\_to\_image template and run it. ```sh pip install -U huggingface_hub ``` ```bash cd ComfyUI/models hf download PedroMarinhoDev/P-JiT-21K-ComfyUI diffusion_models/pjit_21k_bf16.safetensors --local-dir . hf download Comfy-Org/Qwen3.5 text_encoders/qwen3.5_4b_bf16.safetensors --local-dir . ``` ### How to use it Open the ComfyUI-PJiT templates and pick pjit\_text\_to\_image. Linum's settings are already filled in, with 50 steps, the euler sampler, the simple scheduler, a cfg of 15 and an empty negative prompt. Write captions of 50 to 80 words. There is no VAE file, because the built-in pixel\_space option in Load VAE serves as the VAE. | Tool | What it does | | --- | --- | | pjit\_21k\_bf16 | The main model at 4.37 GB, matching Linum's fp32 pixels at half the size | | pjit\_21k\_int8\_convrot | A 2.33 GB model, about 1.8 times faster on GPUs with int8 kernels | | qwen3.5\_4b\_int8\_convrot | A text encoder of 4.72 GB, with caption embeddings 2 percent off | | qwen3.5\_4b\_w4a8 | The smallest text encoder at 3.16 GB, with embeddings 14 to 16 percent off | ### Example You write a 60-word caption of a lighthouse at sunset and run the template with the default settings. The model draws the image directly in pixels after 50 steps. On an RTX 3090 at 1024 by 1024, the card measures about 0.34 seconds per step for the bf16 file. ### For newcomers and experts A text-to-image model turns a written description into a picture. A good first step is to use the bf16 model with the bf16 text encoder and the default template, then try the int8 files if you need more speed. P-JiT works in pixel space, so no VAE decodes the result. The card says bf16 gives the same pixels as the fp32 release at half the size, while int8 trades some fine detail for speed. Among the text encoders, the W4A8 file changes faces the most. You write a 50 to 80 word caption → Qwen3.5-4B text encoder reads it → P-JiT draws directly in pixels → Optional refiner pass polishes the image ### Good to know - License: Apache 2.0. - Cost to run: none named. You need your own GPU with at least 4 GB of free VRAM. - Data it reaches: it downloads files from the Hugging Face Hub, then generates images on your own machine. - Not for: other front ends, or work that needs the finest facial detail with the smallest text encoder. Seconds per step on an RTX 3090 at 1024 by 1024 | Label | Value | | --- | --- | | pjit\_21k\_bf16 | 0.34 seconds | | pjit\_21k\_int8\_convrot | 0.19 seconds | | Linum's fp32 release | 0.35 seconds | ## README ````markdown # P-JiT-21K-ComfyUI Generates images from text prompts inside ComfyUI, using Linum's 2B-parameter P-JiT 21K model in bf16 and int8 files that run from 4 GB of free VRAM. It suits ComfyUI users with modest GPUs. Made by PedroMarinhoDev on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: P-JiT-21K-ComfyUI packages Linum's P-JiT 21K text-to-image model as bf16 and int8 files for ComfyUI. P-JiT is a 2B-parameter model that draws straight in pixels and needs no VAE. Through the ComfyUI-PJiT nodes, generation uses ComfyUI's regular sampler and memory handling and needs only 4 GB of free VRAM. Who it suits: It suits ComfyUI users who want to generate images on a modest GPU and are happy to install custom nodes. ```table Industry | Who uses it | How they use it | Example Design | Visual designers | Generate concept images from written captions | A caption about a Mediterranean street after rain Creative hobby | ComfyUI enthusiasts | Run a small pixel-space model on a mid-range card | Using the int8 files on a 4 GB card Research | Image model researchers | Compare file precisions and text encoders | Reading the card's comparison of bf16, int8 and fp32 ``` People who use other front ends can skip it, since the files are made for ComfyUI. Where to use it: - ComfyUI version 0.44 or newer, with the ComfyUI-PJiT custom nodes - A computer with a GPU, from 4 GB of free VRAM - Windows, macOS or Linux, wherever ComfyUI runs ```table Use case | Who | What they get back Text to image | Designers and hobbyists | Images drawn from captions of 50 to 80 words Refining an image | ComfyUI users | A refiner pass that reworks an image at low denoise Prompt upsampling | Casual users | A workflow that expands a short prompt into a caption ``` How to set it up: - ComfyUI 0.44 or newer - The ComfyUI-PJiT custom nodes, cloned into the custom_nodes folder with no pip install - A GPU with at least 4 GB of free VRAM - Disk space for the model and a text encoder, from about 2.33 GB and 3.16 GB 1. Install the ComfyUI-PJiT nodes and restart ComfyUI. 2. Download the model and a text encoder files into the models folder. 3. Open the pjit_text_to_image template and run it. ```sh pip install -U huggingface_hub ``` ```bash cd ComfyUI/models hf download PedroMarinhoDev/P-JiT-21K-ComfyUI diffusion_models/pjit_21k_bf16.safetensors --local-dir . hf download Comfy-Org/Qwen3.5 text_encoders/qwen3.5_4b_bf16.safetensors --local-dir . ``` How to use it: Open the ComfyUI-PJiT templates and pick pjit_text_to_image. Linum's settings are already filled in, with 50 steps, the euler sampler, the simple scheduler, a cfg of 15 and an empty negative prompt. Write captions of 50 to 80 words. There is no VAE file, because the built-in pixel_space option in Load VAE serves as the VAE. ```table Tool | What it does pjit_21k_bf16 | The main model at 4.37 GB, matching Linum's fp32 pixels at half the size pjit_21k_int8_convrot | A 2.33 GB model, about 1.8 times faster on GPUs with int8 kernels qwen3.5_4b_int8_convrot | A text encoder of 4.72 GB, with caption embeddings 2 percent off qwen3.5_4b_w4a8 | The smallest text encoder at 3.16 GB, with embeddings 14 to 16 percent off ``` Example: You write a 60-word caption of a lighthouse at sunset and run the template with the default settings. The model draws the image directly in pixels after 50 steps. On an RTX 3090 at 1024 by 1024, the card measures about 0.34 seconds per step for the bf16 file. For newcomers and experts: A text-to-image model turns a written description into a picture. A good first step is to use the bf16 model with the bf16 text encoder and the default template, then try the int8 files if you need more speed. P-JiT works in pixel space, so no VAE decodes the result. The card says bf16 gives the same pixels as the fp32 release at half the size, while int8 trades some fine detail for speed. Among the text encoders, the W4A8 file changes faces the most. ```flow You write a 50 to 80 word caption Qwen3.5-4B text encoder reads it P-JiT draws directly in pixels Optional refiner pass polishes the image ``` Good to know: - License: Apache 2.0. - Cost to run: none named. You need your own GPU with at least 4 GB of free VRAM. - Data it reaches: it downloads files from the Hugging Face Hub, then generates images on your own machine. - Not for: other front ends, or work that needs the finest facial detail with the smallest text encoder. ```chart Title: Seconds per step on an RTX 3090 at 1024 by 1024 pjit_21k_bf16: 0.34 seconds pjit_21k_int8_convrot: 0.19 seconds Linum's fp32 release: 0.35 seconds ``` ## On Hugging Face, 13 November 2026 - Task: text to image - Library: comfyui - Downloads in the last 30 days: 0 - Likes: 3 - License: apache-2.0 - Based on: Linum-AI/pjit-21k - Tags: comfyui, text-to-image, pixel-space, pjit, int8, convrot ## Links - Model: https://huggingface.co/PedroMarinhoDev/P-JiT-21K-ComfyUI - Files: https://huggingface.co/PedroMarinhoDev/P-JiT-21K-ComfyUI/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download PedroMarinhoDev/P-JiT-21K-ComfyUI ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [PedroMarinhoDev/P-JiT-21K-ComfyUI on Hugging Face](https://huggingface.co/PedroMarinhoDev/P-JiT-21K-ComfyUI) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | P-JiT-21K-ComfyUI (this page) | 0 | 3 | — | apache-2.0 | 2026-11-05 | | [RelayVSR X4 Quants](https://mindket.com/p/7c045234-17e2-4b4e-bc65-51965af10f9d) | 0 | 7 | — | apache-2.0 | 2026-11-03 | | [Iris-3B by speridlabs](https://mindket.com/p/0abd1bcc-dae6-497c-b706-d6bc43cde2df) | 997 | 350 | 3B | apache-2.0 | 2026-10-12 | | [FLUX.2 Klein 4B for ComfyUI](https://mindket.com/p/52d0d22b-570e-4aee-b125-e557b699311d) | 1,291,519 | 125 | — | apache-2.0 | 2026-10-28 | | [FLUX.1-schnell for ComfyUI](https://mindket.com/p/aafa1823-2bef-4d67-92e4-b409306e9893) | 318,566 | 314 | — | apache-2.0 | 2026-10-28 | | [MOSS-Image-SFT GGUF](https://mindket.com/p/4358c31a-f5e3-45d4-80c7-46f64c71d3ff) | 18,762 | 22 | 5.1B | apache-2.0 | 2026-10-20 | Numbers as Mindket last read them, on 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-05 - First published: 2026-11-05 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open PedroMarinhoDev/P-JiT-21K-ComfyUI on Hugging Face](https://huggingface.co/PedroMarinhoDev/P-JiT-21K-ComfyUI) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/d0a30236-48a7-45cf-86ae-6efd01cf3951) - [Its page on Mindket](https://mindket.com/p/d0a30236-48a7-45cf-86ae-6efd01cf3951)