Colossus Project Flux

Settings and Workflow V2.0:You can run the model now with less steps.. 16 steps equals 30 steps from the old model.I still recommend using around 20- 30 steps because it will get you more quality in most cases.Sampler: I prever Euler with Simple as scheduler. The guidance can be set from 1.5-3 (feel free to test it outside this range of course). The guidance of 1.8 still works well for realistic images. You can also test out other samplers. DPM++2M and Heun also working great.Workflow 2.0:I have created a new workflow for V2.0 and V1.0. This got the new Flux Prompt Generator. Additionally I got the second upscaler stage working. <a target="_blank" rel="ugc" href="https://civitai.com/articles/7946">https://civitai.com/articles/7946</a>

colossusProjectFlux_v20AllInOneExp.safetensors

v2.0_all_in_one_exp.

v12_fp4_nunchaku

v12_int4_SVDQ_nunchaku

V12 Behemoth (AIO)

V12 Q5_1_GGUF_variant_B

V12 "Hephaistos"FP16_UNET

V12 "Hephaistos" FP8_AIO

V12 FP16_UNET_B_variant

V12 "Hephaistos" FP8_UNET

v10_Clip_L

v10B_"BOB"_FP16_UNET_Only

v10B_"BOB"_FP8_UNET_Only

v10_int4_SVDQ

v10B_FP8_AIO "BOB" FP8

v10_UNET_only_FP16

v10_Behemoth_AIO_FP16

v10_UNET_only_FP8

v10_AIO_FP8

v9.0_AIO

v5.0_GGUF_Q8.0

v5.0_AIO_Behemoth

v4.4_AIO

V5.0_Clip_L

v5.0_FP8_UNET

v5.0_AIO

v4.2_AIO

2.1_GGUF_Q8_0

Clip_L_V2.1

2.1_de-distilled_FP8_UNET

2.1_de-distilled_GGUF 4_1

2.1_de-distilled_AIO_exp

v1.0_UNET_Only_GGUF_Q4_1

v1.0_UNET_Only_GGUF_Q8_0

v1.0_UNET_Only_GGUF_Q4_0

v1.0_FP16_UNET_ONLY

v1.0_Clip_L_Colossus_Proj

v1.0_UNET_only_FP8

v1.0_all in one_fp8

Files with SHA256: 1cd06f0b23fb33ff45a9bb31bc750a85c3cc61b2d5700882220b6225b032284f