Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > Nucleus-Image-comfyui-beta

ComfyUI Extension: Nucleus-Image-comfyui-beta

Repo Name

Nucleus-Image-comfyui-beta

Author
a180265 (Account age: 1788 days)
Nodes
View all nodes(1)
Latest Updated
2026-04-22
Github Stars
0.0K

How to Install Nucleus-Image-comfyui-beta

Install this extension via the ComfyUI Manager by searching for Nucleus-Image-comfyui-beta
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter Nucleus-Image-comfyui-beta in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Nucleus-Image-comfyui-beta Description

Nucleus-Image-comfyui-beta adds ComfyUI nodes to load the Nucleus-Image model, encode positive and negative prompts, sample latent images, and decode them with its dedicated VAE into viewable images.

Nucleus-Image-comfyui-beta Introduction

Nucleus-Image-comfyui-beta adds custom nodes to ComfyUI for creating images with the Nucleus-Image 17B MoE diffusion model. It gives you a workflow for loading the model, turning written prompts into guidance, generating an image, and decoding the result into a viewable picture.

The extension is designed around Nucleus-Image’s own components. Its text encoder and image decoder differ from those used by common Stable Diffusion workflows, so the extension provides dedicated loaders rather than relying on ComfyUI’s standard CLIP and VAE loaders. It also includes optional controls for memory use and generation behavior.

This is a beta release. The author has tested image generation with the FP8 model, but has not run the bf16 model because of hardware limitations. Block Swap, CFG Rescale, and Model Shift have passed code review but have not been tested during generation. Treat their results as experimental. The author reports good results with the euler sampler and normal scheduler; other sampler and scheduler combinations have not been established as equally effective.

How Nucleus-Image-comfyui-beta Works

Think of the workflow as a small production line:

  1. Load the image model. The Transformer Loader supplies the part that gradually creates the image.
  2. Translate your prompt. The Text Encoder turns your words into information the image model can use. A positive prompt describes what you want; a negative prompt provides the sampler’s negative guidance.
  3. Generate the underlying image data. The Sampler starts from a seed and refines the result over a chosen number of steps. You can set the image size, guidance strength, sampler, and scheduler here.
  4. Make the image viewable. The VAE Decode node converts the sampler’s latent output, an internal image representation, into a regular image that you can connect to a ComfyUI image output node.

A basic prompted workflow is:

Transformer Loader ───────────────────────────────┐
Text Encoder Loader → Text Encode (Dual) ─────────┼→ Sampler → VAE Decode → image
VAE Loader ────────────────────────────────────────┘

Text Encode (Dual) produces separate positive and negative outputs for the Sampler. The optional Block Swap, Model Shift, and CFG Rescale nodes add controls around this basic flow.

The text encoder loads when a Text Encode node needs it and is released from GPU memory after encoding. The Transformer is offloaded to the CPU after sampling, and the VAE is offloaded after decoding. These behaviors help manage GPU memory, although they do not guarantee that every workflow will fit on every graphics card.

Nucleus-Image-comfyui-beta Features

Dedicated model loaders

  • Transformer Loader selects a Nucleus-Image model from ComfyUI’s diffusion_models directory. Its precision setting offers bf16, fp16, and fp32 for computation; the documented tested configuration uses bf16. The loader detects and handles FP8 model weights automatically. Its load_device setting chooses the initial location of non-expert parameters: offload_device or main_device.
  • Text Encoder Loader selects the Qwen3-VL text encoder from text_encoders and offers the same computation-precision choices. You do not need to choose a loading device: the encoder is loaded when encoding begins and released afterward.
  • VAE Loader selects the matching image decoder from vae and offers bf16, fp16, and fp32 computation precision.

The model file format and the precision setting are different choices. For example, the author’s tested configuration uses FP8 model files with bf16 selected for computation. The source README does not provide comparative image-quality results for the other combinations.

Prompt and conditioning nodes

  • Text Encode turns one multiline prompt into conditioning for either the Sampler’s positive or negative input.
  • Text Encode (Dual) accepts a positive and a negative prompt and produces both outputs while loading the text encoder only once. This is the author’s recommended choice for a typical prompted workflow. The negative prompt can be an empty string ("").
  • Zero Conditioning creates a zero-valued conditioning input without loading the text encoder. The author describes it as an option for unconditional generation or as an alternative negative input. Its appearance may differ from an encoded empty negative prompt.

Generation controls

The Sampler combines the model and conditioning to generate a latent image. Its main settings are:

SettingDefaultWhat it controls
width and height1024 × 1024Output dimensions, adjustable in increments of 64
steps50How many denoising steps the sampler performs
cfg4.0How strongly generation follows the conditioning
seed0The starting random value; keeping it fixed helps you compare setting changes
sampler_nameeulerThe sampling method
scheduler_namenormalHow sampling steps are scheduled

The node offers ComfyUI’s built-in samplers and schedulers. The author specifically reports good results with euler and normal; that is a useful starting point, not a requirement.

The README suggests these image sizes for different compositions:

SizeShapePossible use
1024 × 1024SquareGeneral-purpose images
1344 × 768LandscapeWide scenes
768 × 1344PortraitTall compositions
1280 × 720Widescreen16:9-style images

Optional adjustments

  • Block Swap sets blocks_to_swap from 0 to 29. At 0, blocks stay on the GPU; increasing the value moves more MoE blocks to the CPU. This is intended to help when GPU memory is limited, but the author has not runtime-tested this feature.
  • Model Shift overrides the model’s sigma-shift settings with base_shift and max_shift, which default to 0.5 and 1.15. If you leave the node disconnected, the scheduler configuration supplies its defaults. The author has not runtime-tested this override.
  • CFG Rescale sets an adaptive guidance-normalization strength from 0.0 to 1.0; 1.0 is identified as the official default. The author has not runtime-tested this control, so change it cautiously and compare results with the same seed.

Finally, VAE Decode takes the Sampler’s latent output and the VAE Loader’s output and produces a viewable image.

Nucleus-Image-comfyui-beta Models

The extension works with three model components: a Transformer to generate the image, a Qwen3-VL text encoder to interpret prompts, and a VAE to turn latent output into an image. The source README lists these single-file options:

ComponentFP8 or standard fileOptional bf16 file
Transformernucleus_image_transformer_fp8.safetensors (about 16.9 GB)nucleus_image_transformer_bf16.safetensors (about 31.7 GB)
Text encodernucleus_image_text_encoder_fp8.safetensors (about 8.2 GB)nucleus_image_text_encoder_bf16.safetensors (about 16.5 GB)
VAEnucleus_image_vae.safetensors (about 122 MB)nucleus_image_vae_bf16.safetensors (about 243 MB)

The author recommends FP8 because it uses fewer resources and is faster. The bf16 files are presented as optional higher-quality versions, but bf16 generation has not been run-tested by the author; the README does not provide a measured quality comparison. For a first workflow, use the FP8 files and the tested settings below:

NodeTested setting
Transformer LoaderFP8 transformer; precision: bf16; load_device: offload_device
Text Encoder LoaderFP8 text encoder; precision: bf16
Text Encode (Dual)Positive prompt and negative prompt
Samplersteps: 50; cfg: 4.0; euler sampler; normal scheduler
VAE Loadernucleus_image_vae.safetensors; precision: bf16

Use the matching Nucleus-Image VAE rather than a VAE from another image model. You can find the model’s official page at NucleusAI/Nucleus-Image on Hugging Face.

Troubleshooting Nucleus-Image-comfyui-beta

The image does not seem to follow the prompt

  1. Check that your positive Text Encode output is connected to the Sampler’s positive input.
  2. Connect a negative conditioning output to the Sampler’s negative input as well. The author recommends Text Encode (Dual), even when its negative prompt is empty ("").
  3. Start with the author’s tested euler sampler, normal scheduler, 50 steps, and cfg of 4.0. Keep the seed fixed while checking whether a changed connection or setting helps.

The image looks dark or gray

  1. Check the file selected in VAE Loader.
  2. Select the Nucleus-Image VAE, such as nucleus_image_vae.safetensors, rather than a VAE from another model.
  3. Run the workflow again and compare the decoded result.

Generation runs out of GPU memory

  1. If you are using bf16 model files, try the recommended FP8 files.
  2. Check whether Block Swap helps by increasing blocks_to_swap from its default of 0. The author has not runtime-tested Block Swap, so make small changes and watch for errors.
  3. If needed, try a smaller image size while keeping both dimensions on the Sampler’s 64-pixel increments.

Frequently asked questions

Can I use ComfyUI’s usual CLIPLoader or VAELoader?
No. Nucleus-Image uses a Qwen3-VL text encoder rather than standard CLIP, and its VAE uses a 16-channel latent format. Use the extension’s dedicated loaders.

Why is there no device option on Text Encoder Loader?
The text encoder loads when a Text Encode node runs and is released from the GPU after encoding, so the loader does not require manual device selection.

Do I need to set FP8 quantization manually?
No. According to the source README, Transformer Loader detects FP8 model weights and handles them automatically.

Are all optional controls tested?
No. FP8 inference is the tested path. The author has not runtime-tested Block Swap, Model Shift, or CFG Rescale, and has not run-tested bf16 inference.

Learn More about Nucleus-Image-comfyui-beta

The author states that the node code may be modified, customized, and distributed without restrictions.

Nucleus-Image-comfyui-beta Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Nucleus-Image-comfyui-beta detailed guide | ComfyUI