silveroxides

/

MiniMax-H3_tests

like 32

i'm interested too

dareties works great for r2v also.
use the settings, 0.8 strength, shift 8/3, 6-8 steps, euler simple, or LCM simple.

er_sde ODE with eta 0 / power_shift seems interesting too

guys i am getting this error:

ERROR lora diffusion_model.blocks.15.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384

and it keeps going, using int8 pruned official..

@necroryona

no expert but followed PlagueKind workflow and it fixed my error, if it the correct way? not sure but it did remove the error:

1. create folder: h3_adaln in "ComfyUI/models" folder
2. https://huggingface.co/deAPI-ai/minimax-h3-33b-int8/resolve/main/loras/h3_silu_temb_grid.safetensors put this file in h3_adaln folder
3. 

put this node after your custom lora loader node(if using)

I have that node in my pack

thanks guys i just downloaded plague's new workflow and it's gone now, thanks for both of you.

@necroryona

no expert but followed PlagueKind workflow and it fixed my error, if it the correct way? not sure but it did remove the error:

1. create folder: h3_adaln in "ComfyUI/models" folder
2. https://huggingface.co/deAPI-ai/minimax-h3-33b-int8/resolve/main/loras/h3_silu_temb_grid.safetensors put this file in h3_adaln folder
3. 

put this node after your custom lora loader node(if using)

I tried this with experimental lora /minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095.safetensors
and the result is terrible. Does it not work?

@Rkss
yes im having trouble with this lora also - if using with custom lora , the elements of the custom lora is deformed ... the light x2v 1.1 fl2va lora keep them correctly, maybe im doing something wrong

@Rkss
yes im having trouble with this lora also - if using with custom lora , the elements of the custom lora is deformed ... the light x2v 1.1 fl2va lora keep them correctly, maybe im doing something wrong

https://github.com/Rkkss/ComfyUI-H3-Turbo-LoRA-Bridge

Well, i vibecoded a loader for this lora . Expect some buggy mess, but it works for now. Or wait, someone to prune it

@Rkss
yes im having trouble with this lora also - if using with custom lora , the elements of the custom lora is deformed ... the light x2v 1.1 fl2va lora keep them correctly, maybe im doing something wrong

https://github.com/Rkkss/ComfyUI-H3-Turbo-LoRA-Bridge

Well, i vibecoded a loader for this lora . Expect some buggy mess, but it works for now. Or wait, someone to prune it

this is very good, thanks! i had to install this node to make it work :) https://github.com/Larryvrh/ComfyUI-MiniMax-H3-Turbo

https://huggingface.co/Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_pruned

Pruned Adaln modules. It works with the native LoRA loader
I tested a bit and couldn't determine if these modules made visible differences
It's not 1:1 with the original LoRA, just so you know.

I think silveroxides just released an actual pruned version, loaded fine with the Plaguekind WF/LoRA loader: https://huggingface.co/silveroxides/MiniMax-H3_tests/tree/main/dareties_pruned

don't use rev6, stick to rev2 if you use a resize. rev6 melts under pressure.

don't use rev6, stick to rev2 if you use a resize. rev6 melts under pressure.

Thank you! I actually wasn't aware of that. Was wondering why my gens were still messing up even after I got the pruned one. lol

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

that lora at 0.8 strenght, and samplers ODE and powershift, i swear it just works
and model shift 8/3 or 9/3

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

that lora at 0.8 strenght, and samplers ODE and powershift, i swear it just works
and model shift 8/3 or 9/3

i just tried this and yeah, it does WORK, which loras do you recommend other than the one i mentioned? and if i could bother you with their settings as well, i'd be really thankful.

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

that lora at 0.8 strenght, and samplers ODE and powershift, i swear it just works
and model shift 8/3 or 9/3

i just tried this and yeah, it does WORK, which loras do you recommend other than the one i mentioned? and if i could bother you with their settings as well, i'd be really thankful.

the 768 dareties at like 0.6-0.7 strength with 8 steps and 8/3 shift works good

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

that lora at 0.8 strenght, and samplers ODE and powershift, i swear it just works
and model shift 8/3 or 9/3

i just tried this and yeah, it does WORK, which loras do you recommend other than the one i mentioned? and if i could bother you with their settings as well, i'd be really thankful.

this is my lastes lora stack i tried, it yielded pretty good results on 0.5mp and 6 steps
i also use plaguekind's SLA node, it's a good speedup with few quality compromises, i suggest you cheking their wf and look how it is connected

in your exp guys, what are the best settings (str included) for minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro_pruned ? so far i think it's the best one, because i'm about to lose my mind testing all of these loras.

that lora at 0.8 strenght, and samplers ODE and powershift, i swear it just works
and model shift 8/3 or 9/3

i just tried this and yeah, it does WORK, which loras do you recommend other than the one i mentioned? and if i could bother you with their settings as well, i'd be really thankful.

this is my lastes lora stack i tried, it yielded pretty good results on 0.5mp and 6 steps
i also use plaguekind's SLA node, it's a good speedup with few quality compromises, i suggest you cheking their wf and look how it is connected

Update to nodepack 1.4.0
R2v is nearly matching t2v in speed now on match. And max size is the same or slightly faster than match was.

you dropped the update after i took the ss mr godkind

er_sde ODE with eta 0 / power_shift seems interesting too

loved this one, any other recommendations?