nodes/YRIKKA-ComfyUI-InferenceTimeScaling
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

clarifying auto download of verifiers

Browse Source
This commit is contained in:
MaximClouser
2025-02-26 21:09:48 +00:00
parent 38e8698c40
commit 89b97afb80
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -107,6 +107,8 @@ Loads the Qwen VLM verifier model for image evaluation.
#### Outputs:
- `qwen_verifier_instance`: Loaded Qwen verifier instance
The model will be downloaded automatically on first use (you do not need to have these weights locally beforehand).
### LoadCLIPScoreVerifier Node
Loads the CLIP model for computing text-image similarity scores.
@@ -120,6 +122,8 @@ Loads the CLIP model for computing text-image similarity scores.
#### Outputs:
- `clip_verifier_instance`: Loaded CLIP verifier instance
The model will be downloaded automatically on first use (you do not need to have these weights locally beforehand).
### LoadImageRewardVerifier Node
Loads the ImageReward model for image quality assessment.
@@ -133,6 +137,8 @@ Loads the ImageReward model for image quality assessment.
#### Outputs:
- `image_reward_verifier_instance`: Loaded ImageReward verifier instance
The model will be downloaded automatically on first use (you do not need to have these weights locally beforehand).
## Example Workflow
1. Load your model using the standard ComfyUI checkpoint loader