mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-12 12:37:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Basic Genmo Mochi video model support.

Browse Source 
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.

EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
This commit is contained in:
comfyanonymous
2024-10-26 06:54:00 -04:00
parent c3ffbae067
commit 5cbb01bc2f
18 changed files with 1677 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
comfy/supported_models.py
View File

@@ -10,6 +10,7 @@ import comfy.text_encoders.sa_t5
import comfy.text_encoders.aura_t5
import comfy.text_encoders.hydit
import comfy.text_encoders.flux
import comfy.text_encoders.genmo
from . import supported_models_base
from . import latent_formats
@@ -670,7 +671,36 @@ class FluxSchnell(Flux):
out = model_base.Flux(self, model_type=model_base.ModelType.FLOW, device=device)
return out
class GenmoMochi(supported_models_base.BASE):
unet_config = {
"image_model": "mochi_preview",
}
models = [Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, HunyuanDiT, HunyuanDiT1, Flux, FluxSchnell]
sampling_settings = {
"multiplier": 1.0,
"shift": 1.0,
}
unet_extra_config = {}
latent_format = latent_formats.Mochi
memory_usage_factor = 2.0 #TODO
supported_inference_dtypes = [torch.float16, torch.bfloat16, torch.float32]
vae_key_prefix = ["vae."]
text_encoder_key_prefix = ["text_encoders."]
def get_model(self, state_dict, prefix="", device=None):
out = model_base.GenmoMochi(self, device=device)
return out
def clip_target(self, state_dict={}):
pref = self.text_encoder_key_prefix[0]
t5_detect = comfy.text_encoders.sd3_clip.t5_xxl_detect(state_dict, "{}t5xxl.transformer.".format(pref))
return supported_models_base.ClipTarget(comfy.text_encoders.genmo.MochiT5Tokenizer, comfy.text_encoders.genmo.mochi_te(**t5_detect))
models = [Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, HunyuanDiT, HunyuanDiT1, Flux, FluxSchnell, GenmoMochi]
models += [SVD_img2vid]