Support for Chroma - Flux1 Schnell distilled with CFG (#7355)

* Upload files for Chroma Implementation

* Remove trailing whitespace

* trim more trailing whitespace..oops

* remove unused imports

* Add supported_inference_dtypes

* Set min_length to 0 and remove attention_mask=True

* Set min_length to 1

* get_mdulations added from blepping and minor changes

* Add lora conversion if statement in lora.py

* Update supported_models.py

* update model_base.py

* add uptream commits

* set modelType.FLOW, will cause beta scheduler to work properly

* Adjust memory usage factor and remove unnecessary code

* fix mistake

* reduce code duplication

* remove unused imports

* refactor for upstream sync

* sync chroma-support with upstream via syncbranch patch

* Update sd.py

* Add Chroma as option for the OptimalStepsScheduler node
This commit is contained in:
Silver
2025-05-01 02:57:00 +02:00
committed by GitHub
parent 39c27a3705
commit 4ca3d84277
11 changed files with 667 additions and 4 deletions

View File

@@ -17,6 +17,7 @@ import comfy.text_encoders.hunyuan_video
import comfy.text_encoders.cosmos
import comfy.text_encoders.lumina2
import comfy.text_encoders.wan
import comfy.text_encoders.chroma
from . import supported_models_base
from . import latent_formats
@@ -1068,7 +1069,34 @@ class HiDream(supported_models_base.BASE):
def clip_target(self, state_dict={}):
return None # TODO
class Chroma(supported_models_base.BASE):
unet_config = {
"image_model": "chroma",
}
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, Lumina2, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, Hunyuan3Dv2mini, Hunyuan3Dv2, HiDream]
unet_extra_config = {
}
sampling_settings = {
"multiplier": 1.0,
}
latent_format = comfy.latent_formats.Flux
memory_usage_factor = 3.2
supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32]
def get_model(self, state_dict, prefix="", device=None):
out = model_base.Chroma(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.chroma.ChromaTokenizer, comfy.text_encoders.chroma.chroma_te(**t5_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, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, Lumina2, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, Hunyuan3Dv2mini, Hunyuan3Dv2, HiDream, Chroma]
models += [SVD_img2vid]