Comments (15)
ok, is this fine?
https://www.mediafire.com/file/0e4knd012wv7xg0/Lora.zip/file
from stable-diffusion-webui.
good / bad news
I got a reply from KohakuBlueleaf (who implemented the whole FP8 stuff)
and apparently this is a known issue
good news because it's a know issue
bad news because theres not fix eta
from stable-diffusion-webui.
I cannot reproduce the issue
my test
using xyz to generate 10 images
lora using prompt s/r
: Lora A
+ Lora B
, Lora B
+ Lora A
, Lora A
, Lora B
, blank (no lora)
FP8
: disable
, enable
- since the order of lora dosen't matter, so
Lora A
+Lora B
,Lora B
+Lora A
should produce the same image - comparing
blank
with the twosingle lora
example are diffrent so we can see the lora is working - we can see the behavior is consistent with or without FP8
from stable-diffusion-webui.
I cannot reproduce the issue
my test using xyz to generate 10 images
lora using prompt s/r
:Lora A
+Lora B
,Lora B
+Lora A
,Lora A
,Lora B
,blank (no lora)
FP8
:disable
,enable
- since the order of lora dosen't matter, so
Lora A
+Lora B
,Lora B
+Lora A
should produce the same image- comparing
blank
with the twosingle lora
example are diffrent so we can see the lora is working- we can see the behavior is consistent with or without FP8
Are you on Dev branch?
anyway I'll upload images to explain how "no longer applicable"
from stable-diffusion-webui.
Are you on Dev branch?
yes of course
the use of the term "no longer applicable" is very strange
I think you're trying to say "no longer applied"
I eddited your post and reply to save space
I remember we did wrote in our instructions to "upload" this is sysinfo as opposed to post it in plain text
from stable-diffusion-webui.
yeah that's correct! sorry, my english is too bad ;(
from stable-diffusion-webui.
prompt: score 9, score 8 up, score 7 up, source anime BREAK 1girl, inari_one_(umamusume), handy_fan
negative: monochrome, greyscale, 3d, realistic, source pony, source furry, source cartoon,
base model: ponyxl v6
seed:2476755399
DPM++ 3M SDE Karras / 20steps CFG 7
used loras: https://we.tl/t-tMGd8AMWi3
My results are these. (Sorry for the simplicity. I will provide more information later)
from stable-diffusion-webui.
The test above is with cache fp16 enabled. Even when disabled, the two LoRAs do not seem to be applied simultaneously. (I will post a comparison image later.)
from stable-diffusion-webui.
I'm sorry! I forgot an important piece of information!
As shown below, FP8 appears to break several LoRAs. I have just looked into the details and found that a similar issue was published in January of this year.
#14777
score 9, score 8 up, score 7 up, source anime BREAK 1girl, inari_one_(umamusume), handy_fan
<lora:Inari_one_pony_v3:1>
<lora:pony_handy_fan_r:1>
Negative prompt: monochrome, greyscale, 3d, realistic, source pony, source furry, source cartoon,
Steps: 20, Sampler: DPM++ 3M SDE, Schedule type: Karras, CFG scale: 7, Seed: 2476755399, Size: 1024x1024, Model hash: 67ab2fd8ec, Model: ponyDiffusionV6XL_v6StartWithThisOne, FP8 weight: Enable, Cache FP16 weight for LoRA: True, Clip skip: 2, Hypertile VAE: True, Lora hashes: "Inari_one_pony_v3: 7c1e0c59bfe8, pony_handy_fan_r: 124e98b4a464", Emphasis: No norm, Version: v1.9.4-160-ge33bb8fe
Networks with errors: Inari_one_pony_v3 (32), pony_handy_fan_r (32)
from stable-diffusion-webui.
FP8 is going to change the results, that is to be expected
since your claim is "only the last lora is applyed"
you have to show show that there is meaningful* difference between the results of lora A + lora B
and lora B + lora A
otherwise your demonstration is meaningless
make the full demo as like what I did above
meaningful*: I suspect due to precision / rounding / optimization, the results may not be pixel perfect when the apply order changed, but the results should be fairly similar
if there is not a meaningful difference after the apply order is changed then the issue (if exists) is not "only the last lora is applyed"
in my demo xyz
- you can see that there is a clear difference between the output of no lora and the two single lora
- you can also see there is a clear difference between 2 lora results and the single lora resuls
- but these NO meaningful difference between the resuls when the 2 lora apply order is changed
- the above behavior is consistent with or without FP8
with this information we can determine lora dose work in FP8 regardless of the apply order
whether or not that FP8 breaks certain lora it's not in consideration at the moment
as the issue we are trying to settle here is "only the last lora is applyed"
if the issues of "only the last lora is applyed" exist, then you should see that
- resuls with 2 lora will be diffrent
- the 2 lora result should look like the one lora result
if FP8 breaks some lora (break as in no effect) then you should see that
- one of the single lora result should look like the no lora result
- or 2 lora result should look like single lora result
the we transfer stuff don't work
from stable-diffusion-webui.
I understand. I will create a detailed demo when I have time.
I just confirmed that the same image is output when only pony_handy_fan_r is applied and when both (lora:Inari_one_pony_v3:1 lora:pony_handy_fan_r:1) are applied at the same time
from stable-diffusion-webui.
upload the 2 loras lora:Inari_one_pony_v3
lora:pony_handy_fan_r
see if you can compress them in zip file and upload it hear
if it's too large then use some other method
if you got them from the website like civilai or huggingface then post the links
from stable-diffusion-webui.
still seems to work fine........
I am still not getting
Networks with errors: Inari_one_pony_v3 (32), pony_handy_fan_r (32)
are you sure that the same issue exist across AMD ROCm and NVIDIA
I'm asking others to have a look
from stable-diffusion-webui.
Yes, I have confirmed that it is reproducible on nvidia as well. But yes, it is. I may have a problem with the model of GPU I have, I will buy a new nvidia GPU this month and try it.
(Now tested on RX6600, RTX3060)
from stable-diffusion-webui.
I cannot reproduce the issue
my test using xyz to generate 10 images
lora using prompt s/r
:Lora A
+Lora B
,Lora B
+Lora A
,Lora A
,Lora B
,blank (no lora)
FP8
:disable
,enable
- since the order of lora dosen't matter, so
Lora A
+Lora B
,Lora B
+Lora A
should produce the same image- comparing
blank
with the twosingle lora
example are diffrent so we can see the lora is working- we can see the behavior is consistent with or without FP8
xyz output
Fp8 is enabled? How can I use the feature?
from stable-diffusion-webui.
Related Issues (20)
- [Bug]: RuntimeError: Couldn't install torch. HOT 9
- [Feature Request]: Load safetensors LoRA from AWS s3 bucket URL.
- [Bug]: sd_model.model.diffusion_model.dtype for SDXL still reports float when using --precison half HOT 3
- [Feature Request]: Keep file name toggle on extras batch from directory HOT 1
- [Bug]: AttributeError: 'NoneType' object has no attribute 'lowvram' HOT 5
- OSError: Can't load tokenizer for 'google/t5-v1_1-xxl'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'google/t5-v1_1-xxl' is the correct path to a directory containing all relevant files for a T5TokenizerFast tokenizer. HOT 18
- 如何增加关键词的审核判断呢,例如对接百度的内容审核 HOT 1
- 免费的stable diffusion API, 支持playground, API调用 HOT 2
- [Feature Request]: Update gradio HOT 2
- [Bug]: DPM++ 3M SDE Karras, DPM++ 2M SDE Karras does not appear in Sampling method HOT 2
- [Bug]: Upscaler.py causes infinite loop (fix inside) HOT 2
- [Feature Request]: Auro Flow (Model Support)
- [Bug]: SD3 LoRA HOT 1
- [Feature Request]: clarify in the reamd to set webui.sh. to executable HOT 1
- [Bug]: Git -C command is not recognized by some git versions HOT 3
- [Feature Request]: samplers to be more logically listed HOT 1
- [Bug]: Networkx version error on Ubuntu 20.04 HOT 3
- [Bug]:
- [Bug]: sd_hypernetwork_strength no longer present as an option in quicksettings list
- [Bug]: Installation stalls figuring out if python is installed. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stable-diffusion-webui.