Skip to content

always-gpu tensor error in inpaint mode #1419

Closed
@doer20

Description

@doer20

[Fooocus Model Management] Moving model(s) has taken 0.50 seconds
[Parameters] Adaptive CFG = 7
[Parameters] Sharpness = 2
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 3.0
[Parameters] Seed = 3427956263218991440
[Fooocus] Downloading inpainter ...
[Inpaint] Current inpaint model is /Fooocus/models/inpaint/inpaint_v26.fooocus.patch
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 30 - 15
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Synthetic Refiner Activated
Synthetic Refiner Activated
Request to load LoRAs [['SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors', 0.25], ['None', 1.0], ['None', 1.0], ['None', 1.0], ['None', 1.0]] for model [/data/models/Stable-diffusion/xl/realisticStockPhoto_v10.safetensors].
Loaded LoRA [/Fooocus/models/loras/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors] for UNet [/data/models/Stable-diffusion/xl/realisticStockPhoto_v10.safetensors] with 788 keys at weight 0.25.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] a girl, full focus, cute, intricate, expressive, highly detailed, sharp focused, cinematic, new creative color, elegant, fashionable, beautiful, futuristic, colors spread, symmetry, light, fine detail, joyful, amazing, glowing, attractive, pretty, noble, perfect, lucid, thought, winning, complex, artistic, iconic, clear, brilliant, epic, shining
[Fooocus] Preparing Fooocus text #2 ...
[Prompt Expansion] a girl, very serious, full focus, elegant, intricate, dramatic bright colors, highly detailed, innocent, mystical, enchanted, magic, scenic background, professional, artistic, winning, best, fair, beautiful, cinematic, great composition, original, dynamic, exciting, attractive, creative, positive, lively, awesome, symmetry, perfect, pretty, rational, healthy, pure
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding positive #2 ...
[Fooocus] Encoding negative #1 ...
[Fooocus] Encoding negative #2 ...
[Fooocus] Image processing ...
Upscaling image with shape (661, 661, 3) ...
[Fooocus] VAE Inpaint encoding ...
Requested to load AutoencoderKL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 0.18 seconds
[Fooocus] VAE encoding ...
Traceback (most recent call last):
File "/Fooocus/modules/async_worker.py", line 803, in worker
handler(task)
File "/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Fooocus/modules/async_worker.py", line 598, in handler
pipeline.final_unet = inpaint_worker.current_task.patch(
File "/Fooocus/modules/inpaint_worker.py", line 195, in patch
feed = torch.cat([
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument tensors in method wrapper_CUDA_cat)
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions