Auto Prompter - GPT-4o vision
5.0
0 reviews3
2.9K
561
3
Description
GPT-4o vision version of auto prompter, to produce prompts based on input images, mixing concepts.
More info here:
https://github.com/dagthomas/comfyui_dagthomas
Discussion
(No comments yet)
Loading...
Reviews
No reviews yet
Versions (1)
- latest (a year ago)
Node Details
Primitive Nodes (3)
GPT4VisionNode (1)
PGSD3LatentGenerator (1)
RandomIntegerNode (1)
Custom Nodes (13)
ComfyUI
- LoadImage (2)
- ImageBatch (1)
- PreviewImage (1)
- VAEDecode (1)
- SaveImage (1)
- CLIPTextEncode (2)
- CheckpointLoaderSimple (1)
- KSampler (1)
- easy imageScaleDownToSize (1)
- ShowText|pysssss (1)
- LoadRandomImage (1)
Model Details
Checkpoints (1)
flux\flux1-dev-fp8.safetensors
LoRAs (0)