This is really impressive. It's the first Flux fine-tune that I am really excited about. It has stylistic proportions from Pony but without that overcooked look. It can create some really interesting scenes. I hope you continue working on this and improving it.

This is an awesome model. May I make a suggestion to make the model based on Schnell?

If I may ask. What are you using to animate these images?

the outputs look so great, gave it a try but i always get an error message saying the model cannot be identified. the 11.08 version, is it unet or full checkpoint? wich checkpoint loader node should i use? also, it would be much convenient if you could share the workflow you used to generate with the fp8 11.08 gb version, thanks in advance

now if only the pony loras worked with it we'd be g2g

Looks very good, but unfortunately the breasts are too big.

Cant seem to get this going in comfy ui. Says it couldn't detect the Model type. Using Load Checkpoint

Looks amazing but I'm not able to run it on ForgeUI :(

assert isinstance(state_dict, dict) and len(state_dict) > 16, 'You do not have CLIP state dict!'

AssertionError: You do not have CLIP state dict!

You do not have CLIP state dict!

How can i use it? I dont know ComfyUi, i'm using ForgeUI, need same VAE/CLIPs as Forge Dev fp8?

I cant get the checkpoint to load. I get the error message.

Could not detect model type of: D:\03_SD-Shared-Resources\Checkpoints\[FLUX]ponyish_FLUX_(v1.0).safetensors

"Could not detect model type of: {My_Installation_Path}\[FLUX]ponyish_FLUX_(v1.0).safetensors"

I am able to run other Flux checkpoints though incl Flux1 -D and -S. What might I be missing (using Comfy)?

Where is the FP8 version?

Hey everyone, this is NOT checkpoint but LORA ! I´ve tried Load Diffussion node, Diffusers, Checkpoint too and do nothing or got some errors. But my question is: Exist some trigger words for this ? Thanks