mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-14 05:25:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support hunyuan image 2.1 regular model. (#9792)

Browse Source
This commit is contained in:
comfyanonymous
2025-09-09 23:05:07 -07:00
committed by GitHub
parent 5c33872e2f
commit 85e34643f8
14 changed files with 1906 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
comfy/supported_models.py
View File

@@ -20,6 +20,7 @@ import comfy.text_encoders.wan
import comfy.text_encoders.ace
import comfy.text_encoders.omnigen2
import comfy.text_encoders.qwen_image
import comfy.text_encoders.hunyuan_image
from . import supported_models_base
from . import latent_formats
@@ -1295,7 +1296,31 @@ class QwenImage(supported_models_base.BASE):
hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen25_7b.transformer.".format(pref))
return supported_models_base.ClipTarget(comfy.text_encoders.qwen_image.QwenImageTokenizer, comfy.text_encoders.qwen_image.te(**hunyuan_detect))
class HunyuanImage21(HunyuanVideo):
unet_config = {
"image_model": "hunyuan_video",
"vec_in_dim": None,
}
models = [LotusD, 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, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, FluxSchnell, GenmoMochi, LTXV, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, Lumina2, WAN22_T2V, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, WAN22_Camera, WAN22_S2V, Hunyuan3Dv2mini, Hunyuan3Dv2, Hunyuan3Dv2_1, HiDream, Chroma, ACEStep, Omnigen2, QwenImage]
sampling_settings = {
"shift": 5.0,
}
latent_format = latent_formats.HunyuanImage21
memory_usage_factor = 7.7
supported_inference_dtypes = [torch.bfloat16, torch.float32]
def get_model(self, state_dict, prefix="", device=None):
out = model_base.HunyuanImage21(self, device=device)
return out
def clip_target(self, state_dict={}):
pref = self.text_encoder_key_prefix[0]
hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen25_7b.transformer.".format(pref))
return supported_models_base.ClipTarget(comfy.text_encoders.hunyuan_image.HunyuanImageTokenizer, comfy.text_encoders.hunyuan_image.te(**hunyuan_detect))
models = [LotusD, 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, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, FluxSchnell, GenmoMochi, LTXV, HunyuanImage21, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, Lumina2, WAN22_T2V, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, WAN22_Camera, WAN22_S2V, Hunyuan3Dv2mini, Hunyuan3Dv2, Hunyuan3Dv2_1, HiDream, Chroma, ACEStep, Omnigen2, QwenImage]
models += [SVD_img2vid]