bypassed KSampler with reroute have problems

[dynatron832]

Custom Node Testing

• I have tried disabling custom nodes and the issue persists (see how to disable custom nodes if you need help)

Expected Behavior

a empty latent image from a KSampler that is bypassed through the KSampler should be the same as the input latent of the KSampler. and it should stay empty even if i tunnel it through an reroute node and further to and VAE Decoder.

Actual Behavior

if there is no reroute between the bypassed sampler and the next node i.e. a vae decoder then the workflow works and the resulting image fits to an decoded empty latent.

but if i put a reroute between the bypassed sampler and a vae decoder then this happened ...

Steps to Reproduce

Comfy v0.3.52 portable
take the overall basic node to generate a image. put the Ksampler to bypass mode and put a reroute for the latent output of the sampler and the vae decoder in between. hit run and watch the strange error that appears.

Prompt outputs failed validation:
VAEDecode:
- Return type mismatch between linked nodes: samples, received_type(MODEL) mismatch input_type(LATENT)

Debug Logs

# ComfyUI Error Report
## Error Details
- **Node ID:** N/A
- **Node Type:** N/A
- **Exception Type:** Prompt execution failed
- **Exception Message:** Prompt outputs failed validation: 
VAEDecode:
    - Return type mismatch between linked nodes: samples, received_type(MODEL) mismatch input_type(LATENT)
## Stack Trace

PromptExecutionError@http://127.0.0.1:8188/assets/index-CaymBdIn.js:95259:5
queuePrompt@http://127.0.0.1:8188/assets/index-CaymBdIn.js:95631:13


## System Information
- **ComfyUI Version:** 0.3.52
- **Arguments:** ComfyUI\main.py --windows-standalone-build
- **OS:** nt
- **Python Version:** 3.13.6 (tags/v3.13.6:4e66535, Aug  6 2025, 14:36:00) [MSC v.1944 64 bit (AMD64)]
- **Embedded Python:** true
- **PyTorch Version:** 2.8.0+cu129
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 50x0 : cudaMallocAsync
  - **Type:** cuda
  - **VRAM Total:** 
  - **VRAM Free:** 
  - **Torch VRAM Total:** 0
  - **Torch VRAM Free:** 0

## Logs

2025-08-27T01:28:48.220135 - Checkpoint files will always be loaded safely.
2025-08-27T01:28:48.439331 - Total VRAM  MB, total RAM  MB
2025-08-27T01:28:48.439459 - pytorch version: 2.8.0+cu129
2025-08-27T01:28:48.439946 - Set vram state to: NORMAL_VRAM
2025-08-27T01:28:48.440252 - Device: cuda:0 NVIDIA GeForce RTX 50x0 : cudaMallocAsync
2025-08-27T01:28:49.273158 - Using pytorch attention
2025-08-27T01:28:50.887834 - Python version: 3.13.6 (tags/v3.13.6:4e66535, Aug  6 2025, 14:36:00) [MSC v.1944 64 bit (AMD64)]
2025-08-27T01:28:50.887956 - ComfyUI version: 0.3.52
2025-08-27T01:28:50.915231 - ComfyUI frontend version: 1.25.10
2025-08-27T01:28:50.916129 - [Prompt Server] web root: 
2025-08-27T01:28:51.594669 - 
Import times for custom nodes:
2025-08-27T01:28:51.594796 -    0.0 seconds: \ComfyUI\custom_nodes\websocket_image_save.py
2025-08-27T01:28:51.594982 - 
2025-08-27T01:28:51.786629 - Context impl SQLiteImpl.
2025-08-27T01:28:51.786740 - Will assume non-transactional DDL.
2025-08-27T01:28:51.787558 - No target revision found.
2025-08-27T01:28:51.797047 - Starting server

2025-08-27T01:28:51.797358 - To see the GUI go to: http://127.0.0.1:8188
2025-08-27T01:29:17.424550 - got prompt
2025-08-27T01:29:17.425175 - Failed to validate prompt for output 9:
2025-08-27T01:29:17.425382 - * VAEDecode 8:
2025-08-27T01:29:17.425493 -   - Return type mismatch between linked nodes: samples, received_type(MODEL) mismatch input_type(LATENT)
2025-08-27T01:29:17.425591 - Output will be ignored
2025-08-27T01:29:17.425712 - invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}


## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

{"id":"c5804b39-10c3-43f5-bb64-22c7f41bfd89","revision":0,"last_node_id":10,"last_link_id":11,"nodes":[{"id":7,"type":"CLIPTextEncode","pos":[413,389],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":3,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":5},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[6]}],"properties":{"Node name for S&R":"CLIPTextEncode","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":["text, watermark"]},{"id":6,"type":"CLIPTextEncode","pos":[415,186],"size":[422.84503173828125,164.31304931640625],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":3},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[4]}],"properties":{"Node name for S&R":"CLIPTextEncode","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":["beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"]},{"id":5,"type":"EmptyLatentImage","pos":[473,609],"size":[315,106],"flags":{},"order":0,"mode":0,"inputs":[{"localized_name":"width","name":"width","type":"INT","widget":{"name":"width"},"link":null},{"localized_name":"height","name":"height","type":"INT","widget":{"name":"height"},"link":null},{"localized_name":"batch_size","name":"batch_size","type":"INT","widget":{"name":"batch_size"},"link":null}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[2]}],"properties":{"Node name for S&R":"EmptyLatentImage","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":[512,512,1]},{"id":8,"type":"VAEDecode","pos":[1390.08984375,177.20648193359375],"size":[210,46],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"samples","name":"samples","type":"LATENT","link":11},{"localized_name":"vae","name":"vae","type":"VAE","link":8}],"outputs":[{"localized_name":"IMAGE","name":"IMAGE","type":"IMAGE","slot_index":0,"links":[9]}],"properties":{"Node name for S&R":"VAEDecode","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":[1632.08984375,178.20648193359375],"size":[210,58],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"images","name":"images","type":"IMAGE","link":9},{"localized_name":"filename_prefix","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null}],"outputs":[],"properties":{"Node name for S&R":"SaveImage","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":["ComfyUI"]},{"id":10,"type":"Reroute","pos":[1228.4674072265625,119.4909439086914],"size":[75,26],"flags":{},"order":5,"mode":0,"inputs":[{"name":"","type":"*","link":10}],"outputs":[{"name":"","type":"LATENT","links":[11]}],"properties":{"showOutputText":false,"horizontal":false}},{"id":3,"type":"KSampler","pos":[863,186],"size":[315,262],"flags":{},"order":4,"mode":4,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":1},{"localized_name":"positive","name":"positive","type":"CONDITIONING","link":4},{"localized_name":"negative","name":"negative","type":"CONDITIONING","link":6},{"localized_name":"latent_image","name":"latent_image","type":"LATENT","link":2},{"localized_name":"seed","name":"seed","type":"INT","widget":{"name":"seed"},"link":null},{"localized_name":"steps","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"cfg","name":"cfg","type":"FLOAT","widget":{"name":"cfg"},"link":null},{"localized_name":"sampler_name","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null},{"localized_name":"scheduler","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"denoise","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[10]}],"properties":{"Node name for S&R":"KSampler","cnr_id":"comfy-core","ver":"0.3.52","ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":[156680208700286,"randomize",20,8,"euler","normal",1]},{"id":4,"type":"CheckpointLoaderSimple","pos":[26,474],"size":[315,98],"flags":{},"order":1,"mode":0,"inputs":[{"localized_name":"ckpt_name","name":"ckpt_name","type":"COMBO","widget":{"name":"ckpt_name"},"link":null}],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","slot_index":0,"links":[1]},{"localized_name":"CLIP","name":"CLIP","type":"CLIP","slot_index":1,"links":[3,5]},{"localized_name":"VAE","name":"VAE","type":"VAE","slot_index":2,"links":[8]}],"properties":{"Node name for S&R":"CheckpointLoaderSimple","cnr_id":"comfy-core","ver":"0.3.52","models":[{"name":"v1-5-pruned-emaonly-fp16.safetensors","url":"https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/resolve/main/v1-5-pruned-emaonly-fp16.safetensors?download=true","directory":"checkpoints"}],"ue_properties":{"widget_ue_connectable":{},"version":"7.0.1"}},"widgets_values":["Rev_Animated_v1.2.2.safetensors"]}],"links":[[1,4,0,3,0,"MODEL"],[2,5,0,3,3,"LATENT"],[3,4,1,6,0,"CLIP"],[4,6,0,3,1,"CONDITIONING"],[5,4,1,7,0,"CLIP"],[6,7,0,3,2,"CONDITIONING"],[8,4,2,8,1,"VAE"],[9,8,0,9,0,"IMAGE"],[10,3,0,10,0,"*"],[11,10,0,8,0,"LATENT"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.8338368580060423,"offset":[-47.18115942028999,199.5163043478262]},"ue_links":[],"links_added_by_ue":[]},"version":0.4}

Other

No response

[simula-r]

Hi I was able to reproduce on my end and found Comfy-Org/ComfyUI_frontend#4339 which seems similar. Will raise internally and work on a fix.