CivArchive
    Hunyuan + Flux Sim SCHNELL Unchained - v1512
    NSFW

    It's Schnell Simulacrum v1512 merged in a very specific way with Hunyuan.

    Works with many Flux loras AND Hunyuan loras.

    I know for certain that this is a confusingly derived model, and the inference is different on my ComfyUI. I cannot be certain as to why, and I do not understand as of right now WHY this is happening.

    https://civarchive.com/articles/11578/accidental-discovery-flux-loras-work-on-hunyuan

    There is LITERALLY NO PRECEDENT TO THIS. So if you're expecting some sort of miracle or magical cure-all to merge Flux and Hunyuan this isn't going to happen.

    However, there ARE multiple loras that have very obvious effects to outcome; especially those that train the CLIP_L.

    I repeat, this is a BRAND NEW discovery that I made, and I almost never get attention like this from model releases. In this case I don't have all the answers.

    Just know that I'm looking, and trying to FIND those answers for you all. That's the best I can do for now.

    Consult the article for the ComfyUI flow chart that I used to merge the things. The outcome is essentially the same.

    Combine the merged Hunyuan with OTHER HUNYUAN LORAS to specify more specific outcomes with the system; since this is highly unpredictable and unprecedented currently.


    All the models are compacted.

    To preface... I have no idea how to help you use this. Schnell Sim v1512 was trained heavily on plain English mixed with booru tagging and has full burned pathways for anime, 3d, and realistic. It supports negative prompting and runs optimally between cfg 3.5 and 6; but this isn't Flux, it has different rules, and yet the model works. I'll be working towards a reason in the coming weeks as to why, but as of right this minute I have no idea why.

    I'll need to analyze the call chain and the block loading to see if Comfy's guidance system is somehow introducing T5 into the mix... I actually have about 50 things I need to check.

    /////

    Good luck...

    /////


    I STRONGLY advise the use of loras until I actually train this thing properly.

    Prompt it mixed with actions and Schnell Simulacrum tagging.

    Contents:

    • Hunyuan base model BF16

      • I chose the BF16 because it's the most responsive to the bf16 Schnell Sim.

      • In it's current state is forced to be bf16 until I release a proper checkpoint loader node with quantification attached to each of the subsets.

    • Simulacrum Schnell v1512 BF16 LINK

      • There is a full series of articles and notes on this model; which includes tagging, structures, prompt use, and careful prompt planning.

    • CLIP_24_L_OMEGA BF16

      • This is trained with over 38 million samples at this point. Try not to stub your toe, it can probably identify the bandaid you're looking for.

    • LLAMA FP8

      • This is more conveniently small and moderately fast.

      • It shouldn't impact performance too much

    • Hunyuan BF16 VAE

      • This is the only one that seems to compact correctly and actually yield the correct valuations based on the system.

    Merging Help:

    • ComfyUI:

      • Checkpoint Save Node -> connect all the endpoints of the chain here.

    • Lora Loader:

      • ****

      • We are using this to load the CLIP from the Flux model.

      • If the Flux model does not have a CLIP it will likely not work; but it may.

      • ****

      • The standard Lora loader needs to be used to merge the clip correctly with the CLIP_L omega 24. Hook the model and the clip to it, only hook the OUTPUT from the clip, but not the output from the model.

      • Strength:

        • Model: 0

        • Clip: 1.0

    • Hunyuan Lora Loader:

      • ****

      • We ARE using the models from these now.

      • ****

      • This loads loras by single blocks or double blocks. Loading Flux loras should be loaded by SINGLE BLOCK, at less than 1.0; 1.0 will superimpose TOO MUCH POWER for most loras, and the majority of loras are literally BURNT TO A CRISP so they cannot be used. Lucky for us, Sim Schnell is like a perfectly cooked pot roast and is not burnt at all. It's seared to perfection on low heat over a period of weeks.

      • Strength:

        • Double Blocks: 0.2

        • Single Blocks: 0.8

    • Run both chains to the Checkpoint Save;

      • Model OUT from Hunyuan Lora Model chain

      • Clip OUT from Flux Lora Loader chain

      • VAE OUT from the VAE Load node

    • It will take more than 90 gigs of ram if set to CPU mode TO COMPACT THE MODEL, so bare with it; it takes time to convert a model. I think it took nearly 15 minutes.

    You may now use your merged model; which generates faster, and will utilize many optimizations that the system provides.

    You may be able to load it in many different and unique ways, or compact your own using a similar process.

    This is GROUND WORK; laying foundation for the potential to build something truly great.


    My version of Schnell is protected under a modified Apache 2.0 with the stipulation where small businesses, companies, and research firms may profit from this; but larger corporations and for-profit larger research groups cannot directly profit from this without monetary compensation.

    For Hunyuan's case, I yield the license to Hunyuan for the merge as this isn't my base model. All rights are reserved by the original model creators and there will be no fight if a cease and desist is issued.

    I will make a full apache protected finetune eventually, just not today my friends. Not today.

    I am an independent researcher stationed in the USA and will respect the licensing and rights of the model owners based on local USA law and the implications therein.

    Description

    This isn't... supposed to work.

    Just load it in the main Checkpoint loader in ComfyUI and pray you have the sanity to use it.

    FAQ

    Comments (60)

    crombobularFeb 15, 2025
    CivitAI

    k so what it do tho

    AbstractPhila
    Author
    Feb 15, 2025· 4 reactions

    Many things that it shouldn't do.

    loveaivFeb 15, 2025· 1 reaction

    @AbstractPhila How much vram? Options for poor people? I am cursed with 12gb, pls I do anything.

    AbstractPhila
    Author
    Feb 15, 2025· 1 reaction

    @loveaiv I'll work something out. For now this is just the compacted one because it's convenient.

    crombobularFeb 16, 2025· 5 reactions

    ok be more vague then.

    azeliFeb 16, 2025

    @crombobular yea how stupid is this post so far :D

    AbstractPhila
    Author
    Feb 16, 2025

    @crombobular 

    I released another model immediately before this one named nearly the same thing; and that model is the basis of this one.

    What exactly is the disconnect here? There's a full tag guide there.

    dominic1336756Feb 15, 2025· 4 reactions
    CivitAI

    32Go :(

    AbstractPhila
    Author
    Feb 15, 2025· 3 reactions

    It's a complicated piece of equipment. If I don't ship it like this, I'm almost guaranteeing the majority of you won't use it correctly.

    The download values always reflect incorrectly uniform values. 5 on the clip, 15 on the unet, 7 on the workflow, etc.

    I'll release the broken up one later, but this should be the primary showcase.

    thefoodmageFeb 16, 2025

    I think he meant 32GB

    __vibrating__Feb 15, 2025
    CivitAI

    DO WHUT NOW

    AbstractPhila
    Author
    Feb 15, 2025· 2 reactions

    Yes. I broke all the barriers.

    azeliFeb 16, 2025

    @AbstractPhila Then you need to do a better write up because I'm not sure if anyone even understands what this does !

    DigitalGarbageFeb 16, 2025· 5 reactions
    CivitAI

    UPD: You have to load this model with "Load Checkpoint" node, just like you do with SDXL or SD1.5 models. CLIP and VAE are built-in. What's interesting, it takes less time to render 288x384x33 video than with regular Q5 Hunyuan.

    3427221Feb 16, 2025

    but this don't make much sense, you say in another comment that you go OOM on your setup, so how did you render videos if you go OOM ?

    iamtherealian001Feb 16, 2025· 3 reactions

    @NoArtifact Not sure about @DigitalGarbage but on my 4090 plus 64GB I get one render followed by a crash on the next attempt. So it renders, then goes OOM. I'm getting more luck by being ruthless with the memory management, still pretty flaky though. EDIT: Got it working as an FP8 model, not fully tested it for quality, I have no idea how to prompt it and I'm too tired to work on it right now.

    3427221Feb 16, 2025

    @iamtherealian001 I'll just pass then, got a 3090 too but only 32 gb ram, unless I see video poping that are clearly better than the ones made on Hnyuan base

    OkuresFeb 16, 2025

    @iamtherealian001 How long does the render take perform? I have a similar setup

    MikeflowerFeb 16, 2025

    I have instant crash with checkpoint node.

    AbstractPhila
    Author
    Feb 16, 2025

    @mikebobby681369 I pulled to the newest version of Comfy.

    DigitalGarbageFeb 16, 2025· 3 reactions

    @NoArtifact it's going OOM on the second pass with upscaler or if I set high resolution and/or too many frames for the first pass. I am comparing it with Q5 version of both llama and hunyuan, using fastvideo lora, I could get for even more than 200 frames @ 1280x720 but it takes a lot of time to do.

    This one instead won't allow you to generate any clips longer than 1 second in a good quality, but it is really decent, I should say, in overall comparison results with this merge are more stable in terms of composition, movements and overall character appearance.

    AbstractPhila
    Author
    Feb 16, 2025· 3 reactions

    @DigitalGarbage If you do a manual merge, try setting the double blocks to 0 and single blocks to 1.5, you'll see a tremendous difference. This one is merged at 0.8 single 0.2 double I think.

    I think the 0.2 double blocks impacted the overall interpolation too much.

    iamtherealian001Feb 17, 2025· 1 reaction

    @Okures Sorry for the delay, I had a bit of a disaster trying to fix the cooling on my 5800X, long story short I'm now back to my 6700K which seems to be working a lot better for some reason.

    To answer your question; the hassle wasn't worth it with the raw downloaded model. I could get 105 frames at 384x288 16 steps in about 80 seconds, however that does not include the 5 minutes restarts in between.

    What I've done instead is save out the model without the clip and VAE at BF16. I'm able to use that with the OMEGA 24 CLIP-L that he recommends plus the quantised lllama-Q4_K_M and standard BF16 VAE. That fits in 20.5 GB VRAM plus 30GB RAM and renders in 75 seconds..

    I've used Tensor Cutter to cut it down to FP8. That seems to make no performance difference but gives a different output.

    For all of this I've been using the Fast Lora at 0.7 strength.

    After messing around with it for a bit, I believe this is a good demonstration that we could get some interesting model merges but, for me, the most impressing thing about it is the OMEGA 24 CLIP

    OkuresFeb 17, 2025

    @iamtherealian001 really appreciate the detailed reply. No worries mate.

    Light7799Feb 16, 2025
    CivitAI

    what's the minimum vram needed to run this beast?

    DigitalGarbageFeb 16, 2025

    I suppose it's 24GB. Can't imagine this running with lower VRAM, it goes OOM even on my setup (3090 + 64GB RAM)

    3427221Feb 16, 2025

    @DigitalGarbage save it Fp8 then, probably half the size no ?

    LemonSparkleFeb 16, 2025

    All of it probably x3

    nexusjuan342Feb 16, 2025· 2 reactions

    @DigitalGarbage It's 32gb I'm about to try it on an a6000 48gb on Vast I'll update with results

    AbstractPhila
    Author
    Feb 16, 2025· 1 reaction

    Set your ComfyUI's vram reservation to around 2 gigs reserved for system and just run it. Run the rest using vram dumping nodes.

    There are some nodes to quantify at runtime, find some of those if you need them.

    mrsanders1313840Feb 18, 2025· 2 reactions

    I ran it on 12 GB 4070. The flight is normal in resolution up to 640*480.

    GoronPlusFeb 16, 2025· 2 reactions
    CivitAI

    any chance to prune it below 24 GB?

    CatzFeb 16, 2025· 4 reactions
    CivitAI

    You mention we can use Flux and Hunyuan Lora?

    I tried some Flux lora and it wasn't picking it up. I tried a Character lora and it was not the person at all. I tried a style lora and it doesn't pick it up.
    I've loaded them into a Hunyuan Video LoRA Loader, LoraLoaderModelOnly and Load LoRA node just in case and nope.

    This thing is extremely heavy so couldn't upscale it. Stayed maximum setting at 512x768 at 45 frames 24fps and even reduced to 512x512 for faster result.

    RAM tanked heavily at 63/64GB and vram 23/24GB.

    LatentDreamFeb 16, 2025

    yeah i would also like to have more details about this merging theory and compatibility between hunyuan and flux. Never heard about this before. sounds like a dream .. were all this come from?
    thank yuo

    AbstractPhila
    Author
    Feb 16, 2025· 1 reaction

    @LatentDream It works my friends. It seems to have little response to Flux1D loras; which isn't too shocking.

    I trained Schnell entirely fixated on timesteps, language comprehension, and booru tagging association. I fed nearly the same database into SDXL and sdxl didn't have the intelligence to grasp it.

    The T5 and Flux however, seems to have done just that. It caught it, fixated, and then rationalized it.

    I THINK, the reason this works, is because each lora I trained has the CLIP_L trained alongside it in a low-heat fashion, and the loras themselves are trained specifically on Schnell; which is the heavily timestep-distilled variation of flux.

    Essentially, this implies a few potentials to me.

    1. Flux is inherently still a mystery, and this only adds to the mixing pot.

    2. Timesteps, Shift, and interpolative math are cross-learned and the behaviors are expansive beyond the layers that superimpose those behaviors.

    3. These blocks are divergent in a way that manifests outcome; which is astonishing to me.

    This tells me Shuttle will likely work, if someone extracts a shuttle lora from the Shuttle 1.0 model.

    Shuttle looks better than Simulacrum, and probably trained for a lot longer on higher quality data; but it doesn't have the comprehensive capability due to my absolute fixation on context over quality.

    CatzFeb 16, 2025

    @AbstractPhila You're right, I did use a flux Dev lora. I'll go back to try with a Flux Schnell. There aren't many compare to dev, but I hope this works.

    CatzFeb 16, 2025

    @AbstractPhila Getting no difference with Schnell loras. Can you post an example with a lora that worked for you or is it just in theory that this model should work?

    AbstractPhila
    Author
    Feb 16, 2025

    @Catz Are you loading the loras using the Single Block and Double Block method as I described?

    You must load the Flux lora in multiple hunyuan lora loaders, and then load the clip from said lora to merge with the parent clips from the model.

    This isn't a simple process, which is why I released the compacted version. You need 3 loaders to load one lora.

    thefoodmageFeb 16, 2025

    @AbstractPhila why not share your worflow?

    AbstractPhila
    Author
    Feb 16, 2025· 2 reactions

    @thefoodmage I just made one, I'll share it.

    SDuser666Feb 17, 2025· 1 reaction

    @AbstractPhila The workflow is flowing, but not working as advertised for me. I have not managed to use a FLUX Lora to output what it is supposed to, although a couple times it would result in static noise so it is doing something with the Lora.
    It was especially disappointing to see the model be only kinda willing to make 40k space marines while using FLUX Lora as aids, which bare Hunyuan models I have used so far were moderately good at already. The statement "If it doesn't work, try with a much much higher strength." could be expanded upon. Such as what the single to double block ratio should be or clip strength. The idea is very enticing, but getting there is harder than expected (although the warning was issued). Might this have something to do with me using a 7900 XTX? I do not think so, but mentioning for record.
    The model is still fun to use so maybe it will be my go-to regardless, but damn, still want it to work right.

    AbstractPhila
    Author
    Feb 17, 2025

    @SDuser666 Sorry, not much training with marines in SimSchnellv1512. I'll include more cool shit like this next time.

    magnusfolk314971Feb 17, 2025
    CivitAI

    It didn't work for my loras even with the workflow but I noticed that flux and hunyuan have things in common regarding lora training

    AbstractPhila
    Author
    Feb 17, 2025

    I don't have time to review the entire gradient tape, but I did notice that my particular setup for training Flux Schnell is quite similar in core-elements as the setup used to train Hunyuan as well.

    It's possible my Schnell is an anomaly based entirely on the methodology, captions, and planning I used; and this sort of outcome is a very rare outcome; but I don't think so.

    There's a lot of potential for research exploration but I don't have time today.

    dchan23732Feb 18, 2025
    CivitAI

    I'm confused. Where do I use the 600mb simulacrum file in the workflow? is it another lora?

    AbstractPhila
    Author
    Feb 18, 2025

    It's already merged...? It says right there in the description.

    dchan23732Feb 18, 2025· 1 reaction

    Ah, sorry. Overlooked that.

    AbstractPhila
    Author
    Feb 18, 2025

    @dchan23732 It's okay. I know how complicated this stuff is. Good luck on your journey.

    mrsanders1313840Feb 18, 2025· 2 reactions
    CivitAI

    I used this lora to get an image of a woman, alas, the result was a dark-skinned African woman.

    Not everything seems to be working.

    https://civitai.com/models/975857/ozge-ozacar-turkish-actress?modelVersionId=1092815

    AbstractPhila
    Author
    Feb 18, 2025

    I have... a plan to fix it. It's a 5 stage distillation interpolation, but it needs... a catalyst. I don't have a catalyst picked out yet. There are 12 potential interpolation candidates for this process and so far I'm not liking any of the ones I've found.

    It should be trainable on an a100 though... Maybe on the 5090.

    In any case, the outcome should be a more yielding model.

    The opposite might be true, where I'm just creating a more rigid Hunyuan. So it's hard to say if it'll work right now.

    mrsanders1313840Feb 18, 2025

    @AbstractPhila Maybe you should announce a fundraiser among civitai users? even for 10 dollars, let's say for 100 people, that's enough for something :) Or maybe you should write to the Hunyuan development team? If it were possible to combine hunyuan with flux lora, it would be a jump into space. They would be ahead of many competitors. In any case, I will be looking forward to some kind of result. Well good luck.

    AbstractPhila
    Author
    Feb 18, 2025

    @mrsanders1313840 It's really not going to be very expensive to train. I think I figured out how, actually.

    It's not as complicated as I thought it might be.

    The BULK of information about humans and avatar control is in the VAE, rather than the UNET.

    mrsanders1313840Feb 18, 2025

    I hope everything works out for you and the flux lora will work. By the way, the Chinese are already tuning the hunyuan https://github.com/SkyworkAI/SkyReels-V1

    firemanbrakeneckFeb 18, 2025

    @mrsanders1313840 Hold the phone, that skyreels thing has native I2V?! How good is it?

    AbstractPhila
    Author
    Feb 19, 2025· 1 reaction

    @firemanbrakeneck Probably better than Hunyuan. The Hunyuan paper says they basically focused on avatar faces and upper bodies.

    mrsanders1313840Feb 19, 2025· 1 reaction

    @firemanbrakeneck it was just posted. We'll keep watching. https://huggingface.co/Kijai/SkyReels-V1-Hunyuan_comfy

    mrsanders1313840Feb 19, 2025· 1 reaction

    @AbstractPhila As always, Kijai is the best :) https://huggingface.co/Kijai/SkyReels-V1-Hunyuan_comfy We'll keep watching.

    firemanbrakeneckFeb 19, 2025

    Will hunyuan loras work (perhaps badly, like XL-pony), or was the structure changed significantly?

    Edit: No errors, but poor results.

    SDuser666Feb 23, 2025
    CivitAI

    Based on my (banging rocks together) testing this checkpoint is very impressive and very frustrating. The impressive part is that the checkpoint will almost always produce something good. The frustrating part is that "something good" can be very loosely related to the prompt.
    Can I get a cyborg assassin with the appearance of a 10 year old girl running across the screen towards a robot? No.
    Can I get a cyborg assassin with the appearance of a 10 year old girl running across the screen? No.
    Can I get a cyborg assassin running across the screen? No.

    A panicked crowd? Forget it.
    Characters want to cluster in the center, ages can be under 8 or over 20, they will do a light jog when asked multiple times.
    And yet the consistent quality makes me want to try endlessly...

    AbstractPhila
    Author
    Feb 24, 2025

    Sounds like the intentional age gap burn. Everything with certain traits isn't even supposed to exist, likely being introduced by HunYuan itself rather than Flux.

    Checkpoint
    Hunyuan Video

    Details

    Downloads
    405
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/15/2025
    Updated
    5/13/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.