ComfyUI Node: Paligemma
Run Paligemma without installing ComfyUI
This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.
Category
VLM Nodes/Paligemma
Inputs
image IMAGE
model_id
- gokaygokay/sd3-long-captioner-v2
- Custom
- google/paligemma-3b-ft-refcoco-seg-896
- google/paligemma-3b-ft-cococap-448
- google/paligemma-3b-ft-rsvqa-hr-224
- google/paligemma-3b-ft-science-qa-448
- google/paligemma-3b-ft-vqav2-448
- google/paligemma-3b-mix-224
- google/paligemma-3b-mix-224-jax
- google/paligemma-3b-mix-224-keras
- google/paligemma-3b-mix-448
- google/paligemma-3b-mix-448-jax
- google/paligemma-3b-mix-448-keras
- google/paligemma-3b-pt-224
- google/paligemma-3b-pt-224-jax
- google/paligemma-3b-pt-224-keras
- google/paligemma-3b-pt-448
- google/paligemma-3b-pt-448-jax
- google/paligemma-3b-pt-448-keras
- google/paligemma-3b-pt-896
- google/paligemma-3b-pt-896-jax
- google/paligemma-3b-pt-896-keras
custom_model_id STRING
task_type
- Captioning
- Segmentation
- Question Answering
prompt STRING
precision
- bfloat16
- float32
device
- cpu
- cuda
- cuda:0
- cuda:1
- cuda:2
- cuda:3
quantization
- None
- 8bit
- 4bit
max_tokens INT
min_tokens INT
temperature FLOAT
fill_mask
- True
- False
mask_color STRING
mask_opacity FLOAT
mask_threshold FLOAT
mask_blur INT
Outputs
STRING
MASK
IMAGE
Extension: VLM_nodes
Custom Nodes for Vision Language Models (VLM) , Large Language Models (LLM), Image Captioning, Automatic Prompt Generation, Creative and Consistent Prompt Suggestion, Keyword Extraction
Authored by gokayfem
Looking for a different node?
Run Paligemma without installing ComfyUI
This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.