ComfyUI Node: Load Embedding Model
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Eric/SemanticSearch
Inputs
model_name
- Qwen3-VL-Embedding-2B
- Qwen3-VL-Embedding-8B
device
- auto
- cuda
- cuda:0
- cuda:1
- cpu
max_resolution
- 128x128 (ultra-fast)
- 256x256 (fast)
- 384x384
- 478x478
- 512x512
- 768x768
- 1024x1024 (1MP)
- 1280x1280 (1.6MP)
- 1536x1536 (2.4MP)
attention_type
- sdpa
- eager
- sage
embedding_dim
- Full (4096/2048)
- 2048
- 1024
- 512
- 256
Outputs
EMBEDDING_MODEL
Extension: Eric
Semantic image, video, and document search for ComfyUI using Qwen3-VL multimodal embeddings
Authored by EricRollei
Looking for a different node?
More nodes in Eric
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.