Chroma-Radiance model outputs invalid images

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

### Actual Behavior

### Steps to Reproduce

Run the template workflow.

### Debug Logs

```powershell
(.venv) yuchuxi@WorkStation:~/Servers/ComfyUI$ start --disable-all-custom-nodes
Checkpoint files will always be loaded safely.
Total VRAM 24121 MB, total RAM 95655 MB
pytorch version: 2.8.0+cu129
xformers version: 0.0.32.post2
Set vram state to: NO_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
Using async weight offloading with 2 streams
Using xformers attention
Loading FFmpeg6
Successfully loaded FFmpeg6
Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
ComfyUI version: 0.3.60
Using selector: EpollSelector
ComfyUI frontend version: 1.26.13
[Prompt Server] web root: /home/yuchuxi/Servers/ComfyUI/.venv/lib/python3.12/site-packages/comfyui_frontend_package/static
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_latent.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hypernetwork.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_upscale_model.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_post_processing.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_mask.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_compositing.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_rebatch.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_model_merging.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_tomesd.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_clip_sdxl.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_canny.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_freelunch.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_custom_sampler.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hypertile.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_model_advanced.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_model_downscale.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_images.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_video_model.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_train.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_sag.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_perpneg.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_stable3d.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_sdupscale.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_photomaker.py
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/photomaker
found 1 files
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_pixart.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_cond.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_morphology.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_stable_cascade.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_differential_diffusion.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_ip2p.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_model_merging_model_specific.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_pag.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_align_your_steps.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_attention_multiply.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_advanced_samplers.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_webcam.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_audio.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_sd3.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_gits.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_controlnet.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hunyuan.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_flux.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_lora_extract.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_torch_compile.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_mochi.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_slg.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_mahiro.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_lt.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hooks.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_load_3d.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_cosmos.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_video.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_lumina2.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_wan.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_lotus.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hunyuan3d.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_primitive.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_cfg.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_optimalsteps.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_hidream.py
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/text_encoders
found 8 files
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_fresca.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_apg.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_preview_any.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_ace.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_string.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_camera_trajectory.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_edit_model.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_tcfg.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_context_windows.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_qwen.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_chroma_radiance.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_model_patch.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_easycache.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_extras/nodes_audio_encoder.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/canary.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_ideogram.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_openai.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_minimax.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_veo2.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_kling.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_bfl.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_bytedance.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_luma.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_recraft.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_pixverse.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_stability.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_pika.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_runway.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_tripo.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_moonvalley.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_rodin.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_gemini.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_vidu.py
Trying to load custom node /home/yuchuxi/Servers/ComfyUI/comfy_api_nodes/nodes_wan.py
Skipping loading of custom nodes
Database URL: sqlite:////home/yuchuxi/Servers/ComfyUI/user/comfyui.db
Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: https://0.0.0.0:60080
Feature flags negotiated for client 156253c5483245588a38defa55b2f645: {'supports_preview_metadata': True, 'supports_manager_v4_ui': True}
got prompt
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/vae
found 6 files
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/vae_approx
found 6 files
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/unet
found 1 files
recursive file list on directory /home/yuchuxi/Servers/ComfyUI/models/diffusion_models
found 11 files
Using selector: EpollSelector
Model doesn't have a device attribute.
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
model weight dtype torch.bfloat16, manual cast: None
model_type FLUX
adm 0
Using scaled fp8: fp8 matrix mult: False, scale input: False
Model doesn't have a device attribute.
Requested to load PixArtTEModel_
lowvram: loaded module regularly t5xxl.transformer.shared Embedding(32128, 4096)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.1.DenseReluDense.wo Linear(in_features=10240, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.1.DenseReluDense.wi_1 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.1.DenseReluDense.wi_0 Linear(in_features=4096, out_features=10240, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.SelfAttention.v Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.SelfAttention.q Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.SelfAttention.o Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.SelfAttention.k Linear(in_features=4096, out_features=4096, bias=False)
lowvram: loaded module regularly t5xxl.transformer.encoder.final_layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.9.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.8.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.7.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.6.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.5.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.4.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.3.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.23.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.22.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.21.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.20.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.2.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.19.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.18.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.17.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.16.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.15.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.14.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.13.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.12.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.11.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.10.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.1.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.1.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.layer_norm T5LayerNorm()
lowvram: loaded module regularly t5xxl.transformer.encoder.block.0.layer.0.SelfAttention.relative_attention_bias Embedding(32, 64)
loaded completely 9.5367431640625e+25 4667.387359619141 True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
clip unexpected: ['encoder.embed_tokens.weight']
Requested to load PixArtTEModel_
Warning: TAESD previews enabled, but could not find models/vae_approx/None
Requested to load ChromaRadiance
lowvram: loaded module regularly diffusion_model.single_blocks.9.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.8.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.7.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.6.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.5.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.4.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.37.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.36.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.35.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.34.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.33.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.32.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.31.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.30.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.3.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.29.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.28.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.27.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.26.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.25.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.24.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.23.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.22.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.21.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.20.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.2.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.19.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.18.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.17.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.16.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.15.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.14.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.13.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.12.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.11.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.10.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.1.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.single_blocks.0.pre_norm LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.9.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.9.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.9.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.9.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.8.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.8.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.8.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.8.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.7.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.7.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.7.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.7.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.6.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.6.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.6.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.6.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.5.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.5.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.5.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.5.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.4.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.4.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.4.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.4.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.3.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.3.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.3.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.3.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.2.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.2.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.2.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.2.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.18.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.18.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.18.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.18.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.17.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.17.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.17.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.17.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.16.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.16.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.16.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.16.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.15.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.15.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.15.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.15.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.14.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.14.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.14.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.14.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.13.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.13.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.13.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.13.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.12.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.12.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.12.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.12.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.11.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.11.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.11.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.11.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.10.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.10.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.10.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.10.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.1.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.1.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.1.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.1.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.0.txt_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.0.txt_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.0.img_norm2 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
lowvram: loaded module regularly diffusion_model.double_blocks.0.img_norm1 LayerNorm((3072,), eps=1e-06, elementwise_affine=False)
loaded partially 9.5367431640625e-08 0.0 0
10%|███████████████ | 3/30 [00:51<07:39, 17.03s/it]
```

### Other

(.venv) yuchuxi@WorkStation:~/Servers/ComfyUI$ python -m xformers.info
xFormers 0.0.32.post2
memory_efficient_attention.ckF: unavailable
memory_efficient_attention.ckB: unavailable
memory_efficient_attention.ck_splitKF: unavailable
memory_efficient_attention.cutlassF-pt: available
memory_efficient_attention.cutlassB-pt: available
memory_efficient_attention.fa2F@2.8.2: available
memory_efficient_attention.fa2B@2.8.2: available
memory_efficient_attention.fa3F@2.8.0.post2-3-g3ba6f82: available
memory_efficient_attention.fa3B@2.8.0.post2-3-g3ba6f82: available
memory_efficient_attention.fa3F_splitKV@2.8.0.post2-3-g3ba6f82: available
memory_efficient_attention.triton_splitKF: available
indexing.scaled_index_addF: available
indexing.scaled_index_addB: available
indexing.index_select: available
sp24.sparse24_sparsify_both_ways: available
sp24.sparse24_apply: available
sp24.sparse24_apply_dense_output: available
sp24._sparse24_gemm: available
sp24._cslt_sparse_mm_search@0.7.1: available
sp24._cslt_sparse_mm@0.7.1: available
swiglu.dual_gemm_silu: available
swiglu.gemm_fused_operand_sum: available
swiglu.fused.p.cpp: available
is_triton_available: True
pytorch.version: 2.8.0+cu129
pytorch.cuda: available
gpu.compute_capability: 8.6
gpu.name: NVIDIA GeForce RTX 3090
dcgm_profiler: unavailable
build.info: available
build.cuda_version: 1208
build.hip_version: None
build.python_version: 3.9.23
build.torch_version: 2.8.0+cu128
build.env.TORCH_CUDA_ARCH_LIST: 7.5 8.0+PTX 9.0a
build.env.PYTORCH_ROCM_ARCH: None
build.env.XFORMERS_BUILD_TYPE: Release
build.env.XFORMERS_ENABLE_DEBUG_ASSERTIONS: None
build.env.NVCC_FLAGS: -allow-unsupported-compiler
build.env.XFORMERS_PACKAGE_FROM: wheel-v0.0.32.post2
build.nvcc_version: 12.8.93
source.privacy: open source
(.venv) yuchuxi@WorkStation:~/Servers/ComfyUI$ python -m torch.utils.collect_env
:128: RuntimeWarning: 'torch.utils.collect_env' found in sys.modules after import of package 'torch.utils', but prior to execution of 'torch.utils.collect_env'; this may result in unpredictable behaviour
Collecting environment information...
PyTorch version: 2.8.0+cu129
Is debug build: False
CUDA used to build PyTorch: 12.9
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.3 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: 18.1.3 (1ubuntu1)
CMake version: version 4.1.0
Libc version: glibc-2.39

Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.14.0-32-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090
Nvidia driver version: 580.82.07
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.13.1
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.13.1
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
架构： x86_64
CPU 运行模式： 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
字节序： Little Endian
CPU: 32
在线 CPU 列表： 0-31
厂商 ID： AuthenticAMD
型号名称： AMD Ryzen 9 7950X 16-Core Processor
CPU 系列： 25
型号： 97
每个核的线程数： 2
每个座的核数： 16
座： 1
步进： 2
Frequency boost: enabled
CPU(s) scaling MHz: 68%
CPU 最大 MHz： 6074.0000
CPU 最小 MHz： 545.0000
BogoMIPS： 8982.61
标记： fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d amd_lbr_pmc_freeze
虚拟化： AMD-V
L1d 缓存： 512 KiB (16 instances)
L1i 缓存： 512 KiB (16 instances)
L2 缓存： 16 MiB (16 instances)
L3 缓存： 64 MiB (2 instances)
NUMA 节点： 1
NUMA 节点0 CPU： 0-31
Vulnerability Gather data sampling: Not affected
Vulnerability Ghostwrite: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Mitigation; Safe RET
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected

Versions of relevant libraries:
[pip3] mypy_extensions==1.1.0
[pip3] numpy==2.1.2
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] onnxruntime==1.22.1
[pip3] torch==2.8.0+cu129
[pip3] torchaudio==2.8.0+cu129
[pip3] torchsde==0.2.6
[pip3] torchvision==0.23.0+cu129
[pip3] triton==3.4.0
[conda] Could not collect
(.venv) yuchuxi@WorkStation:~/Servers/ComfyUI$