Work in progress
The models with 📦 mean that are archived and i have yet to update
Check the About this Version of the chose workflow for proper introduction
question, how do i embed the nodes into the images or videos?
if there is a way to load OmniGen/CogVideoX/LLM/t2a/AnimateDiff(gpu) thru a CustomSamplerAdvanced let me know please
Description
Experimental Mochi
Mochi is native on the latests ComfyUI versions, git pull or update.
Sampler:
I recommend chaining samplers of different lines to get the best of each per step, the order is important, i tend to start by 1 step of dpm_adaptative for the success rate, 1 step of sonardpmpp (student-t) for creativity and finish with 3 steps of ipndm & 4 of ddim.
In my examples the Sampler chain is 1 step of dpm_adaptive > 1 step sonar_dpmpp_sde (student-t) > 1 step lcm > 2 steps SamplerDynamicCFGpp > 4 steps heun
The sampler chain for the 5gen/3d style vid is 2 steps SamplerHeunCFGPP > 3 steps idpm > 4 steps ddim
dpm_adaptive|fe_heun3|ae_dopri5(+Guide)
sonar_dpmpp_sde (student/pink|power/uniform)|dpmpp_dual_sde_momentumized| dpm_2_ancestral(+Color)
SamplerDPMCFGpp|heun_cfg_pp|distance_s4e1_cfg_pp|
SamplerCCCFGpp/SamplerDynamicCFGpp|SamplerHeunCFGPP|uni_pc
lcm
dpmpp_2m_sde/*_3m_*|*_gpu
tcd_w
ipndm/majority|heun
SamplerX0CFGpp
to speed up, I normaly generate at 5 steps, and when I find something good I generate it again with at least 9 steps
Noise-types:
3D noises (pyramids,perlin,fractal,voronoi,etc) or laplacian dont work
Work: uniform,power,pink,studentt
Bad: green_test, gaussian
VAE:
You may get an Out of Memory, Until a tiny auto-encoder launch for genmo mochi, Prevent with the argument "--cpu-vae" but takes 6x longer, or use the "latent upscale by" for a fast output (expect blur), or Save latent and decode later.
CFG:
For a successful generation i suggest a cfg greater than 1,
You can get a good image with cfg 1 with a good sampler chain
Scheduler:
Use a primitive for randomizing the alpha and beta parameters for the "BetaSamplingScheduler" until you find your favorite.
Specs:
I have a NVIDIA GeForce GTX 1660 SUP, 6GB vram (like 10 times slower than a 30**/40** series), if i can use this you can as well, probably if you have a good graphics and vram, you may use the correct resolution, correct length and VAEDecode, i didn't try it so it requires experimenting, if you have 4GB vram you can try reducing the length and resolution, but i didn't get good results when testing.