🚀 ComfyUI Auto-Installer — v5 (Python Rewrite)
Version 5 is a full rewrite from the ground up in Python, replacing all the PowerShell scripts from previous versions. It's cross-platform, faster, smarter, and now ships with a TUI manager, Docker images, and GPU-optimized inference out of the box.
If you are upgrading from the PowerShell version (v4.x), a one-command migration preserves all your models, outputs, and custom nodes: irm https://get.umeai.art/migrate.ps1 | iex
⚡ Quick Start (One-Liner)
Windows (PowerShell):
irm https://get.umeai.art/comfyui.ps1 | iexLinux / macOS:
curl -fsSL https://get.umeai.art/comfyui.sh | sh
Only requires Git — everything else (Python, uv, dependencies) is handled automatically.
✨ What's New in v5
Full Python rewrite — no more PowerShell dependency
Cross-platform — Windows, Linux, macOS, and Docker
TUI Manager — interactive terminal UI to launch, update, download models, and configure settings
VRAM-aware model catalog — 7 model families with quantization recommendations based on your GPU
GPU auto-detection — NVIDIA (CUDA 13.0/12.8), AMD (ROCm/DirectML), Apple Silicon (MPS)
SageAttention 2 + 3 — pre-compiled wheels including RTX 50XX Blackwell support
One-click update — update ComfyUI, all nodes, and dependencies with a single command
Model security scanner — detects malicious pickle code in .ckpt/.pt files
Junction architecture — models and outputs persist independently from ComfyUI updates
Docker ready — 4 image variants including a cloud version with JupyterLab for RunPod
📋 Prerequisites
Git
GPU: NVIDIA (CUDA 12.x+), AMD (Radeon RX 6000+), or Apple Silicon (M1+)
Internet connection
Note: Python is automatically installed via uv if not present. No manual Python setup required.
🎨 Model Catalog (7 Families)
Interactive model downloader with VRAM-based recommendations (★ markers) and SHA-256 integrity checks. Each bundle offers multiple quantization variants (fp16, fp8, GGUF Q3→Q8). Downloads are accelerated via aria2c with HuggingFace + ModelScope fallback:
FLUX (Image): Dev, Fill
Z-IMAGE (Image): Turbo
WAN 2.1 (Video): T2V, I2V 480p
WAN 2.2 (Video): I2V, Fun Inpaint, Fun Camera
HiDream (Image): Dev
QWEN (Image Edit): Image Edit
LTX-2 (Video + Audio): Dev
🧩 34 Custom Nodes Included
Additive manifest — never removes user-installed nodes.
Core (always installed): ComfyUI-Manager
UmeAiRT Tier: ComfyUI-UmeAiRT-Sync, ComfyUI-UmeAiRT-Toolkit, ComfyUI-Crystools, ComfyUI-nunchaku
Full Tier (all of the above +): ComfyUI-Impact-Pack, ComfyUI-Impact-Subpack, ComfyUI-GGUF, ComfyUI-mxToolkit, ComfyUI-Custom-Scripts, ComfyUI-KJNodes, ComfyUI-WanVideoWrapper, ComfyUI-VideoHelperSuite, ComfyUI-Frame-Interpolation, rgthree-comfy, ComfyUI-Easy-Use, ComfyUI-HunyuanVideoMultiLora, ComfyUI-Florence2, ComfyUI-MultiGPU, ComfyUI-WanStartEndFramesNative, ComfyUI-Image-Saver, ComfyUI_UltimateSDUpscale, comfyui_controlnet_aux, x-flux-comfyui, ComfyUI-Detail-Daemon, wlsh_nodes, ComfyUI_essentials, ComfyUI-wanBlockswap, Derfuu_ComfyUI_ModdedNodes, ComfyUI_LayerStyle, ComfyUI-Upscaler-Tensorrt, comfyui-vrgamedevgirl, comfyui-int-and-float, was-node-suite-comfyui
⚙️ GPU Optimizations (Auto-Installed)
PyTorch 2.10: CUDA 13.0/12.8, ROCm 7.1, DirectML, MPS
xformers: Memory-efficient attention
Triton: triton-windows / triton (Linux)
SageAttention 2: Unified ABI3 wheels (Windows), per-arch SM80–SM100 (Linux)
SageAttention 3: RTX 50XX Blackwell native (Windows + Linux)
FlashAttention: Linux + NVIDIA only
Nunchaku & InsightFace: Pre-compiled wheels
Additional Python packages auto-installed: facexlib, onnxruntime-gpu, nvidia-ml-py, cupy-cuda13x, imageio-ffmpeg, hf_xet, cython, rotary_embedding_torch, blend_modes, segment_anything, gguf, and more.
🐳 Docker Support
Requires Docker and an NVIDIA GPU: docker run --gpus all -p 8188:8188 -v comfyui-data:/data registry.gitlab.com/umeairt-studio/comfyui-auto_installer-python:latest
latest: ~4 GB — Ready to go with pre-installed PyTorch
latest-cloud: ~4.5 GB — + JupyterLab for RunPod / cloud
latest-lite: ~2 GB — Minimal (installs PyTorch on first run)
latest-lite-cloud: ~2 GB — Lite + JupyterLab
🔒 Security
No external script execution — all logic is internalized
Secure subprocess calls — no shell=True
HTTPS only — all URLs validated
SHA-256 integrity checks on all model downloads
Pickle model scanner — detects malicious code in .ckpt/.pt files
Zip-slip prevention on archive extraction
CI runs Bandit + pip-audit on every push
📂 Post-Installation
Three launcher scripts are generated:
UmeAiRT-Start-ComfyUI: Launch (Performance mode + SageAttention)
UmeAiRT-Start-ComfyUI_LowVRAM: Launch with --lowvram --fp8 for ≤8 GB VRAM
UmeAiRT-Manager: TUI manager (update, download, reinstall, settings)
🔗 Links
Source code: GitLab (https://gitlab.com/UmeAiRT-Studio/ComfyUI-Auto_installer-Python)
Mirror: Codeberg (https://codeberg.org/UmeAiRT)
Ecosystem: UmeAiRT Studio (https://umeai.art)
Description
The ComfyUI base version is now fixed (v0.3.26).
Updated to Python 3.12.9.
Prepared for SageAttention. (guide being written)
FAQ
Comments (20)
Probably a really dumb question, but can I run this and have a different portable copy of comfyui on my machine at the same time without breaking things? I know if I have minconda I can keep the venv seperate and run a separate torch.. I think? I'm just wondering if the installer will automatically upgrade anything system wide that would affect the portable copy.
This version is completely system independent. This allows you to have a native version or several of these without any problems or even interaction.
@UmeAiRT I just installed this comfy and everything was fine, I put a Gen and it worked but I put the T2V model, and although I put an image, it ran and gave me a result. But I wanted an I2V, so I changed it, the image that was already there and I got this error (last paragraph) and then I thought "Well, it must be the image that is a little big, right? And I put the resolution that is 480 by 720 and I have the I2V model that I downloaded from your recommended page, and I hit Run and I get the error: SamplerCustomAdvanced
mat1 and mat2 shapes cannot be multiplied (769x4863 and 5120x5120) Help me with this, please!
PD: I put this LoRa: https://civitai.com/models/1343093?modelVersionId=1541546
- - - -
Prompt executed in 22.41 seconds got prompt Requested to load CLIPVisionModelProjection loaded completely 1817.4141300201416 1208.09814453125 True loaded completely 21074.907173233034 17431.513916015625 True 0%| | 0/10 [00:00<?, ?it/s] Resetting TeaCache state 10%|████████▎ | 1/10 [00:08<01:17, 8.57s/it] TeaCache: Initialized 20%|████████████████▌ | 2/10 [00:13<00:52, 6.60s/it] !!! Exception during processing !!! mat1 and mat2 shapes cannot be multiplied (769x4863 and 5120x5120) Traceback (most recent call last): File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\execution.py", line 327, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\execution.py", line 202, in get_output_data return_values = mapnode_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\execution.py", line 174, in mapnode_over_list process_inputs(input_dict, i) File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\execution.py", line 163, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 657, in sample samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 1008, in sample output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 976, in outer_sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 959, in inner_sample samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 738, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, self.extra_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 174, in sample_euler_ancestral return sample_euler_ancestral_RF(model, x, sigmas, extra_args, callback, disable, eta, s_noise, noise_sampler) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 203, in sample_euler_ancestral_RF denoised = model(x, sigmas[i] s_in, *extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 390, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 939, in call return self.predict_noise(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 942, 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 "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 370, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 206, in calc_cond_batch return executor.execute(model, conds, x_in, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 317, in calccond_batch output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\model_optimization_nodes.py", line 942, in unet_wrapper_function out = model_function(input, timestep, c) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\model_base.py", line 137, in apply_model return comfy.patcher_extension.WrapperExecutor.new_class_executor( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\model_base.py", line 170, in applymodel model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, extra_conds).float() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1739, in wrappedcall_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1750, in callimpl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\ldm\wan\model.py", line 461, in forward return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options)[:, :, :t, :h, :w] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\model_optimization_nodes.py", line 808, in teacache_wanvideo_forward_orig out = blocks_replace[("double_block", i)]({"img": x, "txt": context, "vec": e0, "pe": freqs}, {"original_block": block_wrap, "transformer_options": transformer_options}) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\model_optimization_nodes.py", line 1137, in skip block_out = original_block(new_args) ^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\model_optimization_nodes.py", line 806, in block_wrap out["img"] = block(args["img"], context=args["txt"], e=args["vec"], freqs=args["pe"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1739, in wrappedcall_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1750, in callimpl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\ldm\wan\model.py", line 216, in forward x = x + self.cross_attn(self.norm3(x), context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1739, in wrappedcall_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1750, in callimpl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\ldm\wan\model.py", line 130, in forward k = self.norm_k(self.k(context)) ^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1739, in wrappedcall_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1750, in callimpl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 71, in forward return self.forward_comfy_cast_weights(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\ops.py", line 186, in forward_comfy_cast_weights out = self.forward_ggml_cast_weights(input, args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "P:\- ComfyUI Wan2.1\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\ops.py", line 215, in forward_ggml_cast_weights return torch.nn.functional.linear(input, weight, bias) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: mat1 and mat2 shapes cannot be multiplied (769x4863 and 5120x5120) Prompt executed in 15.12 seconds
@Eliz103 Some people have problems with large images and I'm working on them, but this week I don't have any computers to test WAN workflows, so it's a bit complicated.
@UmeAiRT I understand, but I put an image of the same resolution which is 480 x 720, it reduces it to that. Anyway, the error seems to be solved, I just had to open another window of the workflow that is already installed, very strange, isn't it? Now what I don't understand is... why my videos come out with a resolution of: 3840 x 5760 ? I haven't moved the resolution setting and upscaler is "ratio 2.0" . And just now in my last gen, I increased it to 56 frames and it only gave me a 3 seconds video 😂 emmm what's going on? lol (Now one for 1 second hahaha... mmm I also find it strange that the computer becomes very slow, I have a RTX 4090, i7 13 gen, 32gb ram and m.2 with little free memory but a lot in the main one, even to the point that I can't even use it, I have to wait and the comfy in a Gen was all on a black screen. Well I explain everything that is happening to me right now, in case you know what it is or then you will fix it haha Thank you very much in advance!
@Eliz103 I've corrected this problem with 1.5 but I can't test it because I don't currently have a graphics card. If you want, here is the temporary link: https://huggingface.co/UmeAiRT/ComfyUI-Auto_installer/resolve/main/workflows/WAN2.1-IMG_to_VIDEO_1.5.zip?download=true
@UmeAiRT Ok! I will try it !
@UmeAiRT Ok i will try it!
@UmeAiRT Error: PathchSageAttentionKJ
No module named 'sageattention' 😅 and SamplerCustomAdvanced
mat1 and mat2 shapes cannot be multiplied (769x4863 and 5120x5120)
@UmeAiRT Error: PathchSageAttentionKJ
No module named 'sageattention' 😅 and SamplerCustomAdvanced
mat1 and mat2 shapes cannot be multiplied (769x4863 and 5120x5120)
@Eliz103 set sage attention node not disabled
Stuck on the first question. WIth a 3090 do I want the fast install or the unoptimized one? I know 3090 has 24gb but the way the question is asked sounds like even with the ram, I still don't want the 'unoptimized' model.
I recommend the Optimized Q8 for a 3090.
This is just what the doctor ordered! Thank you! Well prepared installer!
When I run this script, the CMD window appears briefly and then closes. Nothing changes. Can you help me fix this? I'm using Windows 11.
Hey there, I've been wondering if you are aware how I could update it's pytorch? To either pytorch 2.6 cu128 or pytorch 2.7 cu128? Well essentially to the working version for my 5070 ti. Thanks.
use pip to remove and then install the newer version
i used nightly (not recommended)
.\python.exe -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128
goto pyhon_embedded\lib\site-packages and delete all torch folders. Delete xformers folders. Do not delete torchsde folders. Then got back to python_embedded folder. right-click run terminal. Then run ".\python.exe -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128"
goto python_embedded\sagattention folder and run "..\python.exe -s -m pip install -e ."
This will take some time. After it is done. You can run run_nvidia_gpu-sageattention with your rtx 5000 card. This is what worked for me to use my 5080.