Here is the simple workflow. It works on my side and takes about 10 minutes to generate a 0.3 megapixel 15 second video on 4070TI Super + 32GB RAM. I'm not a pro at all, but as I was looking for beginner-friendly workflow, I didn't find any, so here it is
Main features of this workflow:
Optional Turbo along with other LORAs: Load multiple LORAs in comfortable UI, switch the turbo state with one click
Prompt enhancer: using Florence2 to describe the source image and Hermes-3-Llama (and its system prompt), this workflow improves your existing prompt
Simple properties customizer: tired of calculating resolution manually, looking at all the nodes trying to find the required one? No need! Everything is in one subgraph
Please, leave a comment if you used this workflow, it is really important to me. Have a great generations!
Models links:
unet minimax_h3_fl2va_pruned_int8_convrot.safetensors
clip qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
vae minimax_h3_video_vae_int8_convrot.safetensors
audio_vae minimax_h3_audio_vae_fp32.safetensors
turbo lora minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors
llm model hermes-3-llama-3.1-8B-lorablated-q4_k_m.gguf
Custom nodes links:
Description
kek
FAQ
Comments (7)
hi, it is neat and pleasing at first sight but as you use custom nodes, you should provide the links in the description (and/or add the as a note inside the workflow) to the custom nodes and used models like the hermes one.
+ you may refine it with a more "user friendly" lora loader.
will try it later, just my first impression after opening it, a "beginner" workflow shouldn't be a treasure hunt a first.
hi! thanks, will include all the links later
@parakat11ho681 good job for providing the links !
i like pixaroma nodes but for load image and crop node i still prefer obvpm nodes, it may interest you.
https://github.com/chanon/comfyui-obvpm
@Crezjcm will definitely give it a look, thanks!
Thank you for this. This one is really neat, especially for starters.
Appreciate the feedback, thanks!
excellent simple and neat i2v workflow, well layed out (settings/prompt/image input and video result nodes close to each other), a lot of clean work is made in the subgraphs. simple to understand, simple to use. kudos !