with RTX 5090 200GB RAM - ltx 2.3 is broken
with RTX 5090 200GB RAM - ltx 2.3 is broken; it runs out of memory (OOM) when I increase the frame count, but even when I drop it to 120 frames, it still OOMs—despite working perfectly before. I’ve tested it on multiple instances across VAST and RunPod
WORKFLOW: https://github.com/Lightricks/ComfyUI-LTXVideo/issues/522
from large pool | 0 MiB | 0 MiB | 0 B | 0 B |
| from small pool | 0 MiB | 0 MiB | 0 B | 0 B |
|---------------------------------------------------------------------------|
| Active memory | 29878 MiB | 30453 MiB | 0 B | 0 B |
| from large pool | 0 MiB | 0 MiB | 0 B | 0 B |
| from small pool | 0 MiB | 0 MiB | 0 B | 0 B |
|---------------------------------------------------------------------------|
| Requested memory | 0 B | 0 B | 0 B | 0 B |
| from large pool | 0 B | 0 B | 0 B | 0 B |
| from small pool | 0 B | 0 B | 0 B | 0 B |
|---------------------------------------------------------------------------|
| GPU reserved memory | 30880 MiB | 30880 MiB | 0 B | 0 B |
| from large pool | 0 MiB | 0 MiB | 0 B | 0 B |
| from small pool | 0 MiB | 0 MiB | 0 B | 0 B |
|---------------------------------------------------------------------------|
| Non-releasable memory | 0 B | 0 B | 0 B | 0 B |
| from large pool | 0 B | 0 B | 0 B | 0 B |
| from small pool | 0 B | 0 B | 0 B | 0 B |
|---------------------------------------------------------------------------|
| Allocations | 0 | 0 | 0 | 0 |
| from large pool | 0 | 0 | 0 | 0 |
| from small pool | 0 | 0 | 0 | 0 |
|---------------------------------------------------------------------------|
| Active allocs | 0 | 0 | 0 | 0 |
| from large pool | 0 | 0 | 0 | 0 |
| from small pool | 0 | 0 | 0 | 0 |
|---------------------------------------------------------------------------|
| GPU reserved segments | 0 | 0 | 0 | 0 |
| from large pool | 0 | 0 | 0 | 0 |
| from small pool | 0 | 0 | 0 | 0 |
|---------------------------------------------------------------------------|
| Non-releasable allocs | 0 | 0 | 0 | 0 |
| from large pool | 0 | 0 | 0 | 0 |
| from small pool | 0 | 0 | 0 | 0 |
|---------------------------------------------------------------------------|
| Oversize allocations | 0 | 0 | 0 | 0 |
|---------------------------------------------------------------------------|
| Oversize GPU segments | 0 | 0 | 0 | 0 |
|===========================================================================|
[ERROR] Got an OOM, unloading all loaded models.
[INFO] Prompt executed in 70.11 seconds
[INFO] Requested to load LTXAV
[INFO] loaded partially; 27620.41 MB usable, 27580.40 MB loaded, 1208.96 MB offloaded, 40.01 MB buffer reserved, lowvram patches: 407
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
33%|████████████████████████████████████████████████████████▎ | 1/3 [00:04<00:09, 4.58s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
→ [10S] TiledSampler v2.5: carrier wrapper sampling failed (OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 29.60 GiB
Requested : 128.91 MiB
Device limit : 31.36 GiB
Free (according to CUDA): 28.69 MiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB); falling back to plain video for carrier tile
[INFO] 0 models unloaded.
[INFO] Unloaded partially: 635.17 MB freed, 26945.23 MB remains loaded, 40.01 MB buffer reserved, lowvram patches: 787
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
0%| | 0/3 [00:00<?, ?it/s]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[ERROR] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 29.51 GiB
Requested : 550.00 MiB
Device limit : 31.36 GiB
Free (according to CUDA): 28.69 MiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB
[ERROR] Traceback (most recent call last):
File "/workspace/ComfyUI/custom_nodes/10S-Comfy-nodes/latent_tiled_sampler.py", line 923, in sample_tiled
tile_result = guider.sample(
^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1316, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1254, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1229, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 999, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/k_diffusion/sampling.py", line 1288, in sample_euler_ancestral_cfg_pp
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 639, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1202, in call
return self.outer_predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1209, in outer_predict_noise
).execute(x, timestep, model_options, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1212, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 619, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 210, in calc_cond_batch
return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 218, in _calc_cond_batch_outer
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 334, in calc_cond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/model_base.py", line 191, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/model_base.py", line 235, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1885, in _call_impl
return inner()
^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1833, in inner
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/av_model.py", line 1069, in forward
return super().forward(
^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/model.py", line 936, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/model.py", line 989, in _forward
x = self._process_transformer_blocks(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/av_model.py", line 969, in _process_transformer_blocks
vx, ax = block(
^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/av_model.py", line 276, in forward
attn1_out = self.attn1(norm_vx, pe=v_pe, mask=self_attention_mask, transformer_options=transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1885, in _call_impl
return inner()
^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1846, in inner
hook_result = hook(self, args, result)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/custom_nodes/10S-Comfy-nodes/latent_likeness_anchor.py", line 744, in hook
pull = pull * frame_weights.view(1, F_gen_count, 1, 1)
torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 29.60 GiB
Requested : 128.91 MiB
Device limit : 31.36 GiB
Free (according to CUDA): 28.69 MiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/workspace/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 "/workspace/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 "/workspace/ComfyUI/execution.py", line 315, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/workspace/ComfyUI/execution.py", line 303, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/workspace/ComfyUI/custom_nodes/10S-Comfy-nodes/latent_tiled_sampler.py", line 1078, in sample_tiled
tile_samples = guider.sample(
^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1316, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1254, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1229, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 999, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/k_diffusion/sampling.py", line 1288, in sample_euler_ancestral_cfg_pp
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 639, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1202, in call
return self.outer_predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1209, in outer_predict_noise
).execute(x, timestep, model_options, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 1212, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 619, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 210, in calc_cond_batch
return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 218, in _calc_cond_batch_outer
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/samplers.py", line 334, in calc_cond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/model_base.py", line 191, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/model_base.py", line 235, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1885, in _call_impl
return inner()
^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1833, in inner
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/av_model.py", line 1069, in forward
return super().forward(
^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/model.py", line 936, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/model.py", line 975, in _forward
timestep, embedded_timestep, prompt_timestep = self._prepare_timestep(timestep, batch_size, input_dtype, **merged_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/custom_nodes/10S-Comfy-nodes/ltx_reference_enable.py", line 373, in _patched_prepare_timestep
return _ORIGINAL_PREPARE_TIMESTEP(self, timestep, batch_size, hidden_dtype, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/av_model.py", line 775, in _prepare_timestep
av_ca_video_scale_shift_timestep, _ = self.av_ca_video_scale_shift_adaln_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ldm/lightricks/model.py", line 242, in forward
return self.linear(self.silu(embedded_timestep)), embedded_timestep
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/venv/main/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ops.py", line 1288, in forward
output = self.forward_comfy_cast_weights(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ops.py", line 1230, in forward_comfy_cast_weights
x = self._forward(input, weight, bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/comfy/ops.py", line 1201, in _forward
return torch.nn.functional.linear(input, weight, bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 29.51 GiB
Requested : 550.00 MiB
Device limit : 31.36 GiB
Free (according to CUDA): 28.69 MiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB
[INFO] Memory summary:
|===========================================================================|
PyTorch CUDA memory summary, device ID 0
CUDA OOMs: 0
===========================================================================
Metric
---------------------------------------------------------------------------
Allocated memory
from large pool
from small pool
---------------------------------------------------------------------------
Active memory
from large pool
from small pool
---------------------------------------------------------------------------
Requested memory
from large pool
from small pool
---------------------------------------------------------------------------
GPU reserved memory
from large pool
from small pool
---------------------------------------------------------------------------
Non-releasable memory
from large pool
from small pool
---------------------------------------------------------------------------
Allocations
from large pool
from small pool
---------------------------------------------------------------------------
Active allocs
from large pool
from small pool
---------------------------------------------------------------------------
GPU reserved segments
from large pool
from small pool
---------------------------------------------------------------------------
Non-releasable allocs
from large pool
from small pool
---------------------------------------------------------------------------
Oversize allocations
---------------------------------------------------------------------------
Oversize GPU segments
===========================================================================
[ERROR] Got an OOM, unloading all loaded models.
[INFO] Prompt executed in 12.61 seconds
^C[INFO]
Stopped server
Thanks for the detailed report and the full traceback — that really helps.
Unforunately, this isn't a bug in the LTX-2.3 weights or in our LTXVideo nodes. Looking at the stack trace, the crash happens entirely inside a third-party custom node pack you have installed — custom_nodes/10S-Comfy-nodes/ (latent_tiled_sampler.py, latent_likeness_anchor.py, ltx_reference_enable.py). Those nodes wrap and patch the model's forward pass, and that's where it runs out of memory. None of those files are part of our repo.
What you're hitting is a CUDA out-of-memory: ~29.6 GiB allocated against the 5090's 31.36 GiB limit, failing on the next small allocation. Unfortunately the 200 GB of system RAM doesn't help here once the model is loaded onto the GPU.
A couple of suggestions:
- Since the workflow you're running relies on that custom node pack, the best person to help is whoever authored/maintains that workflow and the 10S-Comfy-nodes nodes — they'll know its memory behavior and the right settings. I'd reach out to them directly.
- If you'd like to confirm it's the node pack, try our reference LTX-2.3 workflow with the standard LTXV sampler + tiled VAE decode nodes and the fp8 / low-VRAM loaders. To fit a 32 GB card, also lower resolution/frame count and keep tiled VAE decode enabled.
Happy to help further if you can reproduce it on our stock workflow!