Building the roadmap around what's actually useful to you. Pick the one you'd get the most value from next, and I'll try to turn it into tutorials/workflows.

Has anyone else tried RefMod. I think it's very good. https://youtu.be/2K6-OtV_Vbc If you could incorporate it into your pipeline Andy, I think you would have a powerful option and feature to offer. It's like a quick Lora, you dump all the reference images into a folder, any size, no description or naming convention. Point the RefMod workflow to the folder, and in moments you have a .safetensor file you can load into a RefMod loader node and then into your workflow. I got ChatGPT to customise the H3 Director (seesee75 version) node to add the RefMod loader output (or multiples) as inputs to the Director node, just like any other ref image input. It's like having 20+ reference images per character, location or prop in one input. I have the custom minimax_director.py (replacement) file if anyone wants to experiment with it, but you can also test it in its native workflow. * you can also add audio and video ref samples to the RefMod creation.

Ok so after posting the video the other day where I create character sheets using ChatGPT I decided to make a local node instead. I still think that GPT 2.5 has better detail, but I know a lot of you would like a local workflow, so here you go, have 2! :-)

I decided to try the long-form resume, this way I can save a project (13 chunks) and run 2 chunks at a time then come back to it later and run another 2 chunks without the system crashing trying to run 13 chunks at once. This brought up the question, what if I dont like the results, Im not seeing a way to rerun the chunck that just finished, it seems I have to start with the next chunk (for example chunk 5 if I ran 1/2, then 3/4), but only the newest chunk is retained in long-form, so I thought I would do a seed hunt (by checking the two boxes (seedhunt and seedhunt latent only scouting), enabled the seed hunt group and disabled the Single pass group) but it throws an error, first part of it below, Im guessing you cant do a seed hunt on long-form, and Im not sure what to try next? I could manually remove 11 chunks and only have 2 to run should get me seed hunt functionality, then start over with a fresh 2 chunks for chunk 3/4 and stitch them together but when I consider this as an option I might as well use a regular workflow, unless Im missing something obvious and just it hasn't hit me yet.. Any suggestions (is there way to seed hunt with long-form (many chunks) and only do the last one, or the ability to rerun the last generated chunk (I believe this may solve the issue I'm facing). I hope all of that made sense. Node threw an error during execution. # ComfyUI Error Report ## Error Details - **Node ID:** 388 - **Node Type:** MuseMinimaxDirectorV1_4 - **Exception Type:** ValueError - **Exception Message:** ValueError: Long-Form Resume cannot be combined with Seed Hunt. ## Stack Trace ``` File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 541, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Hi all. Here are some characters I am developing using ChatGPT for a personal project.