TokiToki Internal
Atlas + S3
All runs
ErrorComfyUI

81493403-cb7b-4220-abae-577067333cb1

Queued
Aug 20, 2026, 07:54 PM
Completed
Aug 20, 2026, 07:54 PM
Execution time
3.4s
Outputs
0 · 0 B
Inputs
0
Cached nodes

Failure

RuntimeErrorin CLIPTextEncode (node 6)

VRAM grow failed: 2013757440 bytes

Stack trace
  File "/home/ec2-user/ComfyUI/execution.py", line 542, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/execution.py", line 341, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/execution.py", line 315, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/ec2-user/ComfyUI/execution.py", line 303, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/nodes.py", line 79, in encode
    return (clip.encode_from_tokens_scheduled(tokens), )
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd.py", line 326, in encode_from_tokens_scheduled
    pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd.py", line 395, in encode_from_tokens
    o = self.cond_stage_model.encode_token_weights(tokens)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/text_encoders/lt.py", line 166, in encode_token_weights
    out, pooled, extra = self.gemma3_12b.encode_token_weights(token_weight_pairs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd1_clip.py", line 45, in encode_token_weights
    o = self.encode(to_encode)
        ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd1_clip.py", line 306, in encode
    return self(tokens)
           ^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/venv/lib64/python3.12/site-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/venv/lib64/python3.12/site-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd1_clip.py", line 266, in forward
    embeds, attention_mask, num_tokens, embeds_info = self.process_tokens(tokens, device)
                                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/sd1_clip.py", line 213, in process_tokens
    tokens_embed = self.transformer.get_input_embeddings()(tokens_embed, out_dtype=torch.float32)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/venv/lib64/python3.12/site-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/venv/lib64/python3.12/site-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/text_encoders/llama.py", line 664, in forward
    return super().forward(input_ids, out_dtype=out_dtype) * scale
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 761, in forward
    return self.forward_comfy_cast_weights(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 1460, in forward_comfy_cast_weights
    return super().forward_comfy_cast_weights(input, out_dtype=out_dtype)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 752, in forward_comfy_cast_weights
    weight, bias, offload_stream = cast_bias_weight(self, device=input.device, dtype=out_dtype, offloadable=True)
                                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 321, in cast_bias_weight
    offload_stream = cast_modules_with_vbar([s], dtype, device, bias_dtype, non_blocking)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 164, in cast_modules_with_vbar
    xfer_dest = get_cast_buffer(dest_size)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/comfy/ops.py", line 124, in get_cast_buffer
    buffer = comfy_aimdo.torch.aimdo_to_tensor(cast_buffer.get(buffer_size, cast_buffer_offset), device)
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/venv/lib64/python3.12/site-packages/comfy_aimdo/vram_buffer.py", line 49, in get
    raise RuntimeError(f"VRAM grow failed: {required_size} bytes")

Outputs

0

The run failed before producing any output.

Text prompts

3
Positivenode 5 · CLIPTextEncode · text

Photorealistic live-action cinema, 35mm anamorphic, autumn golden hour, warm amber grade, shallow depth of field, natural skin texture, fine film grain, 16:9 landscape. Beneath the wrought-iron arch of a red-brick university gate, a young woman with auburn hair, freckles and hazel eyes waits with a canvas bag on her shoulder. A young man with dark curly hair, light stubble and a charcoal hoodie walks in from the left and stops in front of her. She looks up and breaks into a warm, surprised smile. He smiles back and speaks to her warmly. Slow dolly push-in holding both faces in frame, dry autumn leaves drifting through the low golden backlight, students walking far behind in soft focus, late sun flaring softly off the ironwork. Audio: footsteps crunching dry leaves, a light breeze in the trees, distant campus chatter, a warm English line of dialogue spoken by the man, her quiet laugh underneath.

Negativenode 6 · CLIPTextEncode · text

vertical 9:16 framing, portrait crop, cartoon, anime, illustration, fantasy lighting, plastic skin, waxy faces, distorted hands, extra limbs, warped features, text, watermark, logo, oversaturated, blurry, low detail, jitter, flicker, morphing faces

1 other text field— sigmas, filenames, and other non-prompt strings the logger swept up

node 27 · ManualSigmas · sigmas

1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0

Input media

0

This run had no input media — it generated from prompts alone.