BeyondImaginationXL_V0_005_Fix
Fixed the issue with model metadata, preventing it from loading in some UIs. Thahks to S1LV3RC01N for help!
BeyondImaginationXL_V0_005
Update: I changed the terms of license. It is now OK to use the model on other generation services. Please, don't forget about crediting me.
Here is the new version of the model. Major update is still coming, but I decided to publish this checkpoint, which has two improvements:
Higher details in images,
Fixed the issue with metadata(actually, no, will have to do some further research)
Recommended settings are the same as before.
BeyondImaginationXL_V0_003
New version is coming soon! Stay tuned!
BeyondImaginationXL is my first attempt to train an SDXL checkpoint. Sure, it's a rookie, but hey, even rockstars had to start somewhere! This checkpoint is like the rebellious offspring of a commercial model I've been cooking up for a few months. It's got attitude, focusing on keeping it real, rocking various visual vibes, finding that sweet spot between work-appropriate and, well, more adventurous content.
Recommended settings are:
Sampler: DPM 2m or 3m
Scheduler: karras
Steps: 30 - 60
CFG: 3-7
Refiner: Not needed
VAE: Baked in
This is a starting point, so feel free to try it, comment, make suggestions, etc. I will be developing it further. The more you try it and comment, the better new versions get!
Further plans:
Looking at the results of my tests here is what I am planning to do:
improve people (both SFW and NSFW), hands and feet
add interior and landscape design styles. That's a part of a commercial project I'm a founder of and future public releases of the model will get some (but not all😉) cool elements from the commercial model
enhance the level of control over the composition of an image
fix the issue with metadata - I've got reports that the model is not properly recognized in some UIs (I use ComfyUI and my own pipeline based on comfy - it works like a charm)
I will not be working on SDXL Turbo models due to inferior quality and licensing policy
what else? - please write in the comments section
About me:
I am a data scientist and I am a founder of startups related to Computer Vision and Generative AI. Please feel free to contact me if you have any commercial ideas to discuss.
Description
Slightly improved detailes.
Hopefully, fixed the bug with lacking metadata (please, let me know if the model is recognised in webui 1.6, 1.7dev, and webui-forge, where there was an issue in v003)
FAQ
Comments (20)
I am receiving an error when dropping it into Stable Diffusion that this is not a safetensors file.
Same error in webui 1.6, 1.7dev, and webui-forge:
Traceback (most recent call last):
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 81, in init
self.metadata = cache.cached_data_for_file('safetensors-metadata', "checkpoint/" + name, filename, read_metadata)
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\cache.py", line 114, in cached_data_for_file
value = func()
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 73, in read_metadata
metadata = read_metadata_from_safetensors(filename)
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 288, in read_metadata_from_safetensors
assert metadata_len > 2 and json_start in (b'{"', b"{'"), f"{filename} is not a safetensors file"
AssertionError: S:\Models\Stable-Diffusion\untested\beyondimaginationxl_v0003.safetensors is not a safetensors file
Thanks for pointing this out. It works well in ComfyUI/ It could be because of the way metadata was saved. I'll look into it when I train the next version, which will hopefully happen soon.
@Askel72 just want to thank you for this great model. In my opinion one or even the best of all. THX Gonzales
PS: I am looking for your next trained model
@Gonzales007 Oh, that's really encouraging, thank you! I am preparing the dataset for the next version so there will be a new release in a few weeks. I hope you will like it even more. While I'm working on it, I would really appreciate if you could write a review for this model :)
@Askel72 i wrote my first review. thx Gonzales
@Gonzales007 Thanks a lot! This is your first review on my first checkpoint :)
@Askel72 Glad to see I'm not the only one having these issues on version 3, is version 5 devoid this problem? I know it mentions in the notes but has someone tested it? edit Version 5 still has the same issue.
@Kaladae I have the same issue but it doesn´t effect to work with by automatic1111.
@Gonzales007 Yeah it won't work with Auto1111. I haven't tried with comfy because there's a reason I do NOT use it.
@Kaladae i think i expressed myself incorrectly. it works for me with automatic 1111. you can see some of my creations at civitai that i have made with this model. But I use automatic1111 locally on my computer.
@Kaladae Are you talking about v005 or v 003 now? I am using my own training pipeline, and I omitted some metadata in v003, but in v005 the metadata required according to the documentation are there - well, at least that's what I thought. :)
@Askel72 both are working, just getting the message that they are no safetensors file, but working
@Gonzales007 Thanks, I will look into it.
@Askel72 it occurred for me with both versions. I have not actually loaded them into A1111 because the few I had tried kept throwing errors and refusing to load. I would then have to reload my website. At that point I stopped and just started reporting issues to the mod authors to see if they had insight. I will try to load it later when I'm home from work in a few hours.
v005 doesn't fix the metadata error in WebUI Forge: reading metadata for S:\Models\Stable-Diffusion\general\realistic\beyondimaginationxl_v0005.safetensors: AssertionError]
Traceback (most recent call last):
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 81, in init
self.metadata = cache.cached_data_for_file('safetensors-metadata', "checkpoint/" + name, filename, read_metadata)
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\cache.py", line 114, in cached_data_for_file
value = func()
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 73, in read_metadata
metadata = read_metadata_from_safetensors(filename)
File "S:\stable-diffusion\stable-diffusion-webui-forge\webui\modules\sd_models.py", line 288, in read_metadata_from_safetensors
assert metadata_len > 2 and json_start in (b'{"', b"{'"), f"{filename} is not a safetensors file"
AssertionError: S:\Models\Stable-Diffusion\general\realistic\beyondimaginationxl_v0005.safetensors is not a safetensors file
@civit77899 Thanks for the traceback, that's very helpful!
I fixed the model and uploaded it to my Google Drive. So you can update the model page if you want to. Model Link
Oh, thank you! So the problem was in the metadata field. I used some nodes from ComfyUI in my training pipeline to save time and one of the nodes I used without looking inside the code was CheckpointSave. Tuns out it saves the model with incorrect metadata.
@Askel72 Yeah it saves model with both incorrect metadata and no embeddings.position_ids key in the small CLIP. But comfyanonymous should have at least fixed the last one a couple of weebs back
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.