[X] The issue is with a specific flow. Please refer to Flows repository if the problem lies with a specific flow.
[X] I’m not sure where the issue is
Bug Description
Hi,
It looks like there are some issues with the cogvideo text to video and similar templates
it replyes CogVideoxFunSampler is not available
I am not sure, but I think it may have changed and is now CogVideoX_Fun_I2VSampler
altough I changed this, I don t manage to use it.
I was wondering if loading wf.json in comfyui should work without flow ui , isn't it ?
Step-by-step instructions to reproduce the issue
open the t2v cogvideo template
Expected Behavior
I suppose that should work
Current Behavior
replies CogVideoXFunSampler not available
Flow Version or Commit
0.3.3
Media and Logs
I hacked a bit my comfyui implementation to show backtrace and message
got prompt
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\main.py", line 262, in <module>
loop.run_until_complete(run(server, address=args.listen, port=args.port, verbose=not args.dont_print_server, call_on_start=call_on_start))
File "asyncio\base_events.py", line 641, in run_until_complete
File "asyncio\windows_events.py", line 321, in run_forever
File "asyncio\base_events.py", line 608, in run_forever
File "asyncio\base_events.py", line 1936, in _run_once
File "asyncio\events.py", line 84, in _run
File "C:\APPLIS\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\web_protocol.py", line 477, in _handle_request
resp = await request_handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\web_app.py", line 559, in _handle
return await handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\web_middlewares.py", line 117, in impl
return await handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\server.py", line 63, in cache_control
response: web.Response = await handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\server.py", line 141, in origin_only_middleware
response = await handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\server.py", line 75, in cors_middleware
response = await handler(request)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\server.py", line 618, in post_prompt
valid = execution.validate_prompt(prompt)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\execution.py", line 803, in validate_prompt
m = validate_inputs(prompt, o, validated)
File "C:\APPLIS\ComfyUI_windows_portable\ComfyUI\execution.py", line 614, in validate_inputs
traceback.print_stack()
the prompt {'1': {'inputs': {'model': 'THUDM/CogVideoX-5b', 'precision': 'bf16', 'fp8_transformer': 'disabled', 'compile': 'disabled', 'enable_sequential_cpu_offload': False}, 'class_type': 'DownloadAndLoadCogVideoModel', '_meta': {'title': '(Down)load CogVideo Model'}}, '11': {'inputs': {'enable_vae_tiling': False, 'tile_sample_min_height': 96, 'tile_sample_min_width': 96, 'tile_overlap_factor_height': 0.083, 'tile_overlap_factor_width': 0.083, 'auto_tile_size': True, 'pipeline': ['34', 0], 'samples': ['34', 1]}, 'class_type': 'CogVideoDecode', '_meta': {'title': 'CogVideo Decode'}}, '20': {'inputs': {'clip_name': 'Comfyuianonymous\\t5xxl_fp8_e4m3fn.safetensors', 'type': 'sd3'}, 'class_type': 'CLIPLoader', '_meta': {'title': 'Load CLIP'}}, '30': {'inputs': {'prompt': "a white goat with black horns , sporting sleek puprle sunglasses, with its lengthy fur flowing in the breeze, sprints playfully across a rooftop terrace, recently refreshed by a light rain. The scene unfolds from a distance, the goat's energetic bounds growing larger as it approaches the camera, its tail wagging with unrestrained joy, while droplets of water glisten on the concrete behind it. The overcast sky provides a dramatic backdrop, emphasizing the vibrant golden coat of the canine as it dashes towards the viewer.", 'strength': 1, 'force_offload': True, 'clip': ['20', 0]}, 'class_type': 'CogVideoTextEncode', '_meta': {'title': 'CogVideo TextEncode'}}, '31': {'inputs': {'prompt': 'blur,low resolution', 'strength': 1, 'force_offload': True, 'clip': ['20', 0]}, 'class_type': 'CogVideoTextEncode', '_meta': {'title': 'CogVideo TextEncode'}}, '33': {'inputs': {'frame_rate': 20.0, 'loop_count': 0, 'filename_prefix': 'CogVideoX5B', 'format': 'video/h264-mp4', 'pix_fmt': 'yuv420p', 'crf': 19, 'save_metadata': True, 'pingpong': False, 'save_output': True, 'images': ['11', 0]}, 'class_type': 'VHS_VideoCombine', '_meta': {'title': 'Video Combine 🎥🅥🅗🅢'}}, '34': {'inputs': {'height': 480, 'width': 720, 'num_frames': 49, 'steps': 30, 'cfg': 6, 'seed': 141452228539463, 'scheduler': 'CogVideoXDPMScheduler', 'denoise_strength': 1, 'pipeline': ['1', 0], 'positive': ['30', 0], 'negative': ['31', 0]}, 'class_type': 'CogVideoSampler', '_meta': {'title': 'CogVideo Sampler'}}}
Failed to validate prompt for output 33:
* CogVideoDecode 11:
- Exception when validating inner node: tuple index out of range
Output will be ignored
Where is the issue?
Bug Description
Hi, It looks like there are some issues with the cogvideo text to video and similar templates
it replyes CogVideoxFunSampler is not available
I am not sure, but I think it may have changed and is now CogVideoX_Fun_I2VSampler
altough I changed this, I don t manage to use it.
I was wondering if loading wf.json in comfyui should work without flow ui , isn't it ?
Step-by-step instructions to reproduce the issue
open the t2v cogvideo template
Expected Behavior
I suppose that should work
Current Behavior
replies CogVideoXFunSampler not available
Flow Version or Commit
0.3.3
Media and Logs
Additional Information
No response