HELPLESS WITH THESE THREE ERRORS - PLEASE GUIDE TO RECTIFY?

[tmprabubiz]

WINDOWS 10 PRO PC / i9 PROCESSOR / GPU: RTX 2060 SUPER 8GB / CPU: 64GB / USING SYMLINKS INSTEAD OF DEFINING PATHS IN ARGUMENTS

1. I WANT TO AVOID THIS WARNING THAT COMES FIRST WHILE STARTING THE FORGE

J:\webui_forge_cu121_torch231\system\python\lib\site-packages\transformers\utils\hub.py:127: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead.
warnings.warn(<<<
===============================================================================

2. HOW TO RECTIFY THIS VARIABLE SETTING

Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False}<<
================================================================================

3. WHENEVER I CHANGE THE FLUX MODELS, WHY FORGE CHECKS ALL THE EMBEDDINGS AS BELOW
ac_neg1.png: no embedded information found.
AS-YoungV2-neg.png: no embedded information found.
BadDream.png: no embedded information found.
bad_prompt_version2-neg.png: no embedded information found.
comicbookpencils.png: no embedded information found.
easynegative.png: no embedded information found.
FastNegativeV2.png: no embedded information found.
ImgFixerPre0.3.png: no embedded information found.
NEG-fixl-2.png: no embedded information found.
negativeXL_D.png: no embedded information found.
negative_hand-neg.png: no embedded information found.
ng_deepnegative_v1_75t.png: no embedded information found.
unaestheticXL_bp5.png: no embedded information found.
verybadimagenegative_v1.3.png: no embedded information found

👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇👇
NOW THE COMMAND PROMPTS FROM STARTING TO GENERATION (HIGHLIGHTED THE ERRORS SAID ABOVE)

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-304-g394da019
Commit hash: 394da01
CUDA 12.1
Launching Web UI with arguments: --precision full --opt-split-attention --always-batch-cond-uncond --no-half --skip-torch-cuda-test --cuda-malloc --cuda-stream --theme dark
Using cudaMallocAsync backend.
Total VRAM 8192 MB, total RAM 65447 MB
pytorch version: 2.3.1+cu121
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2060 SUPER : cudaMallocAsync
VAE dtype preferences: [torch.float32] -> torch.float32
CUDA Using Stream: True
J:\webui_forge_cu121_torch231\system\python\lib\site-packages\transformers\utils\hub.py:127: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead.
warnings.warn(
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: J:\webui_forge_cu121_torch231\webui\models\ControlNetPreprocessor
22:43:41 - ReActor - STATUS - Running v0.7.1-a1 on Device: CUDA
2024-08-17 22:43:50,873 - ControlNet - INFO - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\FLUX.1-schnell-dev-merged-fp8-4step.safetensors', 'hash': '9e0fb423'}, 'additional_modules': [], 'unet_storage_dtype': 'nf4'}
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Startup time: 28.7s (prepare environment: 4.5s, launcher: 2.5s, import torch: 4.7s, initialize shared: 0.2s, other imports: 1.1s, list SD models: 0.4s, load scripts: 3.3s, initialize extra networks: 7.6s, create ui: 2.9s, gradio launch: 1.5s).
Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False}
Model selected: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\flux1DevSchnellBNB_flux1DevBNBNF4.safetensors', 'hash': '0184473b'}, 'additional_modules': [], 'unet_storage_dtype': 'nf4'}
Loading Model: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\flux1DevSchnellBNB_flux1DevBNBNF4.safetensors', 'hash': '0184473b'}, 'additional_modules': [], 'unet_storage_dtype': 'nf4'}
[Unload] Trying to free 953674316406250018963456.00 MB for cuda:0 with 0 models keep loaded ...
StateDict Keys: {'transformer': 2350, 'vae': 244, 'text_encoder': 198, 'text_encoder_2': 220, 'ignore': 0}
Using Detected T5 Data Type: torch.float8_e4m3fn
Working with z of shape (1, 16, 32, 32) = 16384 dimensions.
K-Model Created: {'storage_dtype': 'nf4', 'computation_dtype': torch.float16}

ac_neg1.png: no embedded information found.
AS-YoungV2-neg.png: no embedded information found.
BadDream.png: no embedded information found.
bad_prompt_version2-neg.png: no embedded information found.
comicbookpencils.png: no embedded information found.
easynegative.png: no embedded information found.
FastNegativeV2.png: no embedded information found.
ImgFixerPre0.3.png: no embedded information found.
NEG-fixl-2.png: no embedded information found.
negativeXL_D.png: no embedded information found.
negative_hand-neg.png: no embedded information found.
ng_deepnegative_v1_75t.png: no embedded information found.
unaestheticXL_bp5.png: no embedded information found.
verybadimagenegative_v1.3.png: no embedded information found.

Model loaded in 9.0s (unload existing model: 0.2s, forge model load: 8.8s).
Skipping unconditional conditioning when CFG = 1. Negative Prompts are ignored.
To load target model JointTextEncoder
Begin to load 1 model
[Unload] Trying to free 7725.00 MB for cuda:0 with 0 models keep loaded ...
[Memory Management] Current Free GPU Memory: 7136.91 MB
[Memory Management] Required Model Memory: 5154.62 MB
[Memory Management] Required Inference Memory: 1024.00 MB
[Memory Management] Estimated Remaining GPU Memory: 958.29 MB
Moving model(s) has taken 5.64 seconds
Distilled CFG Scale: 3.5
To load target model KModel
Begin to load 1 model
[Unload] Trying to free 9411.13 MB for cuda:0 with 0 models keep loaded ...
[Unload] Current free memory is 1159.67 MB ...
[Unload] Unload model JointTextEncoder
[Memory Management] Current Free GPU Memory: 7095.57 MB
[Memory Management] Required Model Memory: 6246.84 MB
[Memory Management] Required Inference Memory: 1024.00 MB
[Memory Management] Estimated Remaining GPU Memory: -175.28 MB
[Memory Management] Loaded to CPU Swap: 1461.51 MB (blocked method)
[Memory Management] Loaded to GPU: 4785.26 MB
Moving model(s) has taken 7.78 seconds
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [01:17<00:00, 3.88s/it]
To load target model IntegratedAutoencoderKL████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [01:12<00:00, 3.82s/it]
Begin to load 1 model
[Unload] Trying to free 8991.55 MB for cuda:0 with 0 models keep loaded ...
[Unload] Current free memory is 2063.04 MB ...
[Unload] Unload model KModel
[Memory Management] Current Free GPU Memory: 6895.08 MB
[Memory Management] Required Model Memory: 319.75 MB
[Memory Management] Required Inference Memory: 1024.00 MB
[Memory Management] Estimated Remaining GPU Memory: 5551.33 MB
Moving model(s) has taken 2.14 seconds
Warning: Ran out of memory when regular VAE decoding, retrying with tiled VAE decoding.
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:05<00:00, 5.44s/it]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:05<00:00, 5.40s/it]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:04<00:00, 4.36s/it]
Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [01:31<00:00, 4.55s/it]
T

PLEASE GUIDE TO RECTIFY THESE ERRORS

[JollyRoger112]

Did you find an answer?

[tmprabubiz]

NO. I could not find the answer. Following is the one I copied now after starting the Forge and generating an image with flux model

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-531-g210af4f8
Commit hash: 210af4f
CUDA 12.1
Launching Web UI with arguments: --disable-xformers --precision full --opt-split-attention --always-batch-cond-uncond --no-half --skip-torch-cuda-test --cuda-malloc --cuda-stream --theme dark
Using cudaMallocAsync backend.
Total VRAM 8192 MB, total RAM 65451 MB
pytorch version: 2.3.1+cu121
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2060 SUPER : cudaMallocAsync
VAE dtype preferences: [torch.float32] -> torch.float32
CUDA Using Stream: True
J:\webui_forge_cu121_torch231\system\python\lib\site-packages\transformers\utils\hub.py:127: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead.
warnings.warn(
Using pytorch cross attention
Using pytorch attention for VAE
ControlNet preprocessor location: J:\webui_forge_cu121_torch231\webui\models\ControlNetPreprocessor
22:26:24 - ReActor - STATUS - Running v0.7.1-a2 on Device: CUDA
2024-09-17 22:26:35,339 - ControlNet - INFO - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\flux1-dev.safetensors', 'hash': 'b04b3ba1'}, 'additional_modules': ['J:\webui_forge_cu121_torch231\webui\models\VAE\ae.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\clip_l.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\t5xxl_fp16.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Startup time: 60.6s (prepare environment: 16.6s, import torch: 13.5s, initialize shared: 0.4s, other imports: 1.8s, list SD models: 0.1s, load scripts: 8.3s, initialize extra networks: 9.0s, create ui: 7.3s, gradio launch: 3.4s).
Environment vars changed: {'stream': False, 'inference_memory': 1874.0, 'pin_shared_memory': False}
[GPU Setting] You will use 77.12% GPU memory (6317.00 MB) to load weights, and use 22.88% GPU memory (1874.00 MB) to do matrix computation.
Model selected: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\fluxArtfusion4Steps_v12_2.safetensors', 'hash': '24779e58'}, 'additional_modules': ['J:\webui_forge_cu121_torch231\webui\models\VAE\ae.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\clip_l.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\t5xxl_fp16.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Loading Model: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\fluxArtfusion4Steps_v12_2.safetensors', 'hash': '24779e58'}, 'additional_modules': ['J:\webui_forge_cu121_torch231\webui\models\VAE\ae.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\clip_l.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\t5xxl_fp16.safetensors'], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'transformer': 776, 'vae': 244, 'text_encoder': 196, 'text_encoder_2': 220, 'ignore': 0}
Using Default T5 Data Type: torch.float16
Using Detected UNet Type: torch.float8_e4m3fn
Working with z of shape (1, 16, 32, 32) = 16384 dimensions.
K-Model Created: {'storage_dtype': torch.float8_e4m3fn, 'computation_dtype': torch.float16}
ac_neg1.png: no embedded information found.
AS-YoungV2-neg.png: no embedded information found.
BadDream.png: no embedded information found.
bad_prompt_version2-neg.png: no embedded information found.
comicbookpencils.png: no embedded information found.
easynegative.png: no embedded information found.
FastNegativeV2.png: no embedded information found.
ImgFixerPre0.3.png: no embedded information found.
NEG-fixl-2.png: no embedded information found.
negativeXL_D.png: no embedded information found.
negative_hand-neg.png: no embedded information found.
ng_deepnegative_v1_75t.png: no embedded information found.
unaestheticXL_bp5.png: no embedded information found.
verybadimagenegative_v1.3.png: no embedded information found.
Calculating sha256 for J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\fluxArtfusion4Steps_v12_2.safetensors: 6168beb7a39c4a49a689d56f5f1ec048836807885c6e7f605310bf7e4bb9cd4b
Model loaded in 10.4s (unload existing model: 0.3s, forge model load: 10.1s).
Skipping unconditional conditioning when CFG = 1. Negative Prompts are ignored.
[Unload] Trying to free 14314.34 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 7136.91 MB, Model Require: 9569.49 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: -4306.59 MB, CPU Swap Loaded (blocked method): 5622.00 MB, GPU Loaded: 4019.87 MB
Moving model(s) has taken 4.51 seconds
Distilled CFG Scale will be ignored for Schnell
[Unload] Trying to free 16616.41 MB for cuda:0 with 0 models keep loaded ... Current free memory is 1459.30 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 7095.84 MB, Model Require: 11340.31 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: -6118.47 MB, CPU Swap Loaded (blocked method): 7344.00 MB, GPU Loaded: 3996.31 MB
Moving model(s) has taken 9.09 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:22<00:00, 5.64s/it]
[Unload] Trying to free 6617.87 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2134.55 MB ... Unload model KModel Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 7092.41 MB, Model Require: 319.75 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: 4898.67 MB, All loaded to GPU.
Moving model(s) has taken 2.02 seconds
Total progress: 100%|████████████████████████████████████████████████████████████████████| 4/4 [00:15<00:00, 3.75s/it]
Total progress: 100%|████████████████████████████████████████████████████████████████████| 4/4 [00:15<00:00, 3.09s/it]

[DenOfEquity]

1. Transformers library will at some point change the environment variable it uses to identify cache location. You can edit environment.bat in the base install directory. The last line is set TRANSFORMERS_CACHE=...; you can just delete that line, or if you want to specify the location change it to set HF_HOME=.... Forge already sets HF_HOME internally.
2. Not an error, or even a warning. Just information relating to how Forge is managing memory.
3. Settings -> Extra Networks -> Print a list of Textual Inversion embeddings when loading model. And/or rename the preview PNGs to {name}.preview.png.

edit:
If you've used Spaces, there may be models downloaded to the TRANSFORMERS_CACHE - default location: {Forge install directory}\system\transformers-cache. You can simply move the contents of that directory to the HF_HOME location, which by default is {Forge install directory}\webui\models\diffusers.

[tmprabubiz]

Thank You. Everything worked well. Very happy.

I did this - Settings -> Extra Networks -> Print a list of Textual Inversion embeddings when loading model

I could not find this - And/or rename the preview PNGs to {name}.preview.png.

Please guide

[DenOfEquity]

that last one isn't an option in the settings. Open the directory where you've saved your embeddings, and rename the preview images so instead of being {name}.png they are {name}.preview.png. This is so the loader knows they are preview images, not images with embeddings inside.

[tmprabubiz]

Oh..... I don't know how I missed it. Thank You. Please have a look at my command prompt for mistakes

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-535-gb20cb4bf
Commit hash: b20cb4b
CUDA 12.1
Launching Web UI with arguments: --disable-xformers --precision full --opt-split-attention --always-batch-cond-uncond --no-half --skip-torch-cuda-test --cuda-malloc --cuda-stream --theme dark
Using cudaMallocAsync backend.
Total VRAM 8192 MB, total RAM 65451 MB
pytorch version: 2.3.1+cu121
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2060 SUPER : cudaMallocAsync
VAE dtype preferences: [torch.float32] -> torch.float32
CUDA Using Stream: True
Using pytorch cross attention
Using pytorch attention for VAE
ControlNet preprocessor location: J:\webui_forge_cu121_torch231\webui\models\ControlNetPreprocessor
01:49:39 - ReActor - STATUS - Running v0.7.1-a2 on Device: CUDA
Textual inversion embeddings loaded(21): ac_neg1, AS-YoungV2-neg, Asian-Less2-Neg, bad_prompt_version2-neg, BadDream, BeyondSDXLv3, comicbookpencils, CXL-Home, CXL-Mech, detailxl, easynegative, FastNegativeV2, ImgFixerPre0.3, NEG-fixl-2, negative_hand-neg, negativeXL_D, ng_deepnegative_v1_75t, pureerosface_v1, realisticvision-negative-embedding, unaestheticXL_bp5, verybadimagenegative_v1.3
2024-09-21 01:49:42,274 - ControlNet - INFO - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\fluxArtfusion4Steps_v12.safetensors', 'hash': '24779e58'}, 'additional_modules': ['J:\webui_forge_cu121_torch231\webui\models\VAE\ae.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\clip_l.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\t5xxl_fp16.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Startup time: 30.2s (prepare environment: 7.7s, import torch: 6.8s, initialize shared: 0.1s, other imports: 0.5s, load scripts: 4.1s, initialize extra networks: 0.9s, initialize google blockly: 0.2s, create ui: 6.7s, gradio launch: 3.1s).
Environment vars changed: {'stream': False, 'inference_memory': 1874.0, 'pin_shared_memory': False}
[GPU Setting] You will use 77.12% GPU memory (6317.00 MB) to load weights, and use 22.88% GPU memory (1874.00 MB) to do matrix computation.
Loading Model: {'checkpoint_info': {'filename': 'J:\webui_forge_cu121_torch231\webui\models\Stable-diffusion\Flux\fluxArtfusion4Steps_v12.safetensors', 'hash': '24779e58'}, 'additional_modules': ['J:\webui_forge_cu121_torch231\webui\models\VAE\ae.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\clip_l.safetensors', 'J:\webui_forge_cu121_torch231\webui\models\text_encoder\t5xxl_fp16.safetensors'], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'transformer': 776, 'vae': 244, 'text_encoder': 196, 'text_encoder_2': 220, 'ignore': 0}
Using Default T5 Data Type: torch.float16
Using Detected UNet Type: torch.float8_e4m3fn
Working with z of shape (1, 16, 32, 32) = 16384 dimensions.
K-Model Created: {'storage_dtype': torch.float8_e4m3fn, 'computation_dtype': torch.float16}
NEG-fixl-2preview.png: no embedded information found.
Model loaded in 1.7s (unload existing model: 0.3s, forge model load: 1.4s).
Skipping unconditional conditioning when CFG = 1. Negative Prompts are ignored.
[Unload] Trying to free 14314.34 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 7136.91 MB, Model Require: 9569.49 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: -4306.59 MB, CPU Swap Loaded (blocked method): 5622.00 MB, GPU Loaded: 4019.87 MB
Moving model(s) has taken 2.60 seconds
Distilled CFG Scale will be ignored for Schnell
[Unload] Trying to free 16616.41 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2573.59 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 7095.57 MB, Model Require: 11340.31 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: -6118.74 MB, CPU Swap Loaded (blocked method): 7344.00 MB, GPU Loaded: 3996.31 MB
Moving model(s) has taken 3.98 seconds
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:20<00:00, 5.08s/it]
[Unload] Trying to free 8991.55 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3095.27 MB ... Unload model KModel Done.████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:13<00:00, 3.69s/it]
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 7091.60 MB, Model Require: 319.75 MB, Previously Loaded: 0.00 MB, Inference Require: 1874.00 MB, Remaining: 4897.85 MB, All loaded to GPU.
Moving model(s) has taken 1.84 seconds
Total progress: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:17<00:00, 4.34s/it]
T

Why does it say "Using online LoRAs in FP16: False"