You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm running my ComfyUI as a server. I'm using the exact same workflow, and the only thing that changes is the model. Even though I'm using --highvram, the model is still partially reloading when I swap checkpoints.
It adds about a 2-4 second overhead when context switching between models.
Is there a way to keep my models 100% in VRAM so there is no overhead to context switching?
Here's an example generation without switching the Model:
When I change the model, I expect it to really quickly be able to swap from VRAM but I get:
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
clip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight']
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
lora key not loaded: lora_te_text_model_encoder_layers_0_mlp_fc1.alpha
...
Requested to load SD1ClipModel
Loading 1 new model
Requested to load SD1ClipModel
Loading 1 new model
Requested to load BaseModel
Loading 1 new model
100%|█████████████████████████████████████████████████████████| 5/5 [00:02<00:00, 2.44it/s]
Requested to load AutoencoderKL
Loading 1 new model
Prompt executed in 4.69 seconds
The text was updated successfully, but these errors were encountered:
I'm running my ComfyUI as a server. I'm using the exact same workflow, and the only thing that changes is the model. Even though I'm using --highvram, the model is still partially reloading when I swap checkpoints.
It adds about a 2-4 second overhead when context switching between models.
Is there a way to keep my models 100% in VRAM so there is no overhead to context switching?
Here's an example generation without switching the Model:
When I change the model, I expect it to really quickly be able to swap from VRAM but I get:
The text was updated successfully, but these errors were encountered: