jinx/ComfyUI
1
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-03 07:26:31 +08:00
Code Issues Activity

Support Lightricks LTX-Video model.

Browse Source
This commit is contained in:
comfyanonymous
2024-11-22 08:44:42 -05:00
parent 2fd9c1308a
commit 5e16f1d24b
15 changed files with 1934 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
comfy/supported_models.py
View File

@@ -11,6 +11,7 @@ import comfy.text_encoders.aura_t5
import comfy.text_encoders.hydit
import comfy.text_encoders.flux
import comfy.text_encoders.genmo
import comfy.text_encoders.lt
from . import supported_models_base
from . import latent_formats
@@ -702,7 +703,34 @@ class GenmoMochi(supported_models_base.BASE):
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))
class LTXV(supported_models_base.BASE):
unet_config = {
"image_model": "ltxv",
}
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]
sampling_settings = {
"shift": 2.37,
}
unet_extra_config = {}
latent_format = latent_formats.LTXV
memory_usage_factor = 2.7
supported_inference_dtypes = [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.LTXV(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.lt.LTXVT5Tokenizer, comfy.text_encoders.lt.ltxv_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, LTXV]
models += [SVD_img2vid]